Methods for improved transmission control protocol (TCP) performance visibility and devices thereof

Abstract

Methods, non-transitory computer readable media, network traffic management apparatuses, and network traffic management systems that generate a duration corresponding to a current one of a plurality of states in a TCP connection. The duration is generated based on a difference between a stored time recorded at a previous transition to the current one of the states and a current time. The duration is stored or output as associated with the current one of the states. The stored time recorded at the previous transition to the current one of the states is then replaced with the current time. A determination is made when one or more TCP configurations should be modified based on the duration for the current one of the states. The one or more TCP configurations are automatically modified to improve TCP performance, when the determining indicates that the one or more TCP configurations should be modified.

Description

FIELD

This technology generally relates to network traffic management and, more particularly, to methods and devices for improved Transmission Control Protocol (TCP) performance visibility.

BACKGROUND

Network devices are often misconfigured in ways that reduce Transmission Control Protocol (TCP) performance, resulting in data loss and/or slow exchanges of data across TCP connections, for example. One exemplary network device that utilizes TCP connections is a network traffic management apparatus that may perform load balancing, application acceleration, and/or security management functions on behalf of a server pool, for example, among many other possible functions. Unfortunately, network administrators do not currently have sufficient visibility with respect to TCP connections to address performance issues exhibited by network traffic management apparatuses, such as by adjusting particular TCP configuration(s).

SUMMARY

A method for improved Transmission Control Protocol (TCP) performance implemented by a network traffic management system comprising one or more network traffic management apparatuses, client devices, or server devices, the method including generating a duration corresponding to a current one of a plurality of states in a TCP connection. The duration is generated based on a difference between a stored time recorded at a previous transition to the current one of the states and a current time. The duration is stored or output as associated with the current one of the states. The stored time recorded at the previous transition to the current one of the states is then replaced with the current time. A determination is made when one or more TCP configurations should be modified based on the duration for the current one of the states. The one or more TCP configurations are automatically modified to improve TCP performance, when the determining indicates that the one or more TCP configurations should be modified.

A network traffic management apparatus, comprising memory comprising programmed instructions stored thereon and one or more processors configured to be capable of executing the stored programmed instructions to generate a duration corresponding to a current one of a plurality of states in a TCP connection. The duration is generated based on a difference between a stored time recorded at a previous transition to the current one of the states and a current time. The duration is stored or output as associated with the current one of the states. The stored time recorded at the previous transition to the current one of the states is then replaced with the current time. A determination is made when one or more TCP configurations should be modified based on the duration for the current one of the states. The one or more TCP configurations are automatically modified to improve TCP performance, when the determining indicates that the one or more TCP configurations should be modified.

A non-transitory computer readable medium having stored thereon instructions for improved TCP performance comprising executable code which when executed by one or more processors, causes the processors to generate a duration corresponding to a current one of a plurality of states in a TCP connection. The duration is generated based on a difference between a stored time recorded at a previous transition to the current one of the states and a current time. The duration is stored or output as associated with the current one of the states. The stored time recorded at the previous transition to the current one of the states is then replaced with the current time. A determination is made when one or more TCP configurations should be modified based on the duration for the current one of the states. The one or more TCP configurations are automatically modified to improve TCP performance, when the determining indicates that the one or more TCP configurations should be modified.

A network traffic management system, comprising one or more network traffic management apparatuses, client devices, or server devices, the network traffic management system comprising memory comprising programmed instructions stored thereon and one or more processors configured to be capable of executing the stored programmed instructions to generate a duration corresponding to a current one of a plurality of states in a TCP connection. The duration is generated based on a difference between a stored time recorded at a previous transition to the current one of the states and a current time. The duration is stored or output as associated with the current one of the states. The stored time recorded at the previous transition to the current one of the states is then replaced with the current time. A determination is made when one or more TCP configurations should be modified based on the duration for the current one of the states. The one or more TCP configurations are automatically modified to improve TCP performance, when the determining indicates that the one or more TCP configurations should be modified.

This technology has a number of associated advantages including providing methods, non-transitory computer readable media, network traffic management apparatuses, and network traffic management systems that more effectively and automatically adjust TCP configurations to improve performance of managed TCP connections. With this technology, durations that TCP connections are in particular states can be determined and analyzed to identify particular configurations that could be adjusted to improve performance. As a result, this technology facilitates reduced latency and improved network communications.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram of an exemplary network traffic management system with an network traffic management apparatus;

FIG. 2 is a block diagram of an exemplary network traffic management apparatus;

FIG. 3 is a flowchart of an exemplary method for determining state durations in a Transmission Control Protocol (TCP) connection; and

FIG. 4 is a flowchart of an exemplary method for determining whether a TCP connection has transitioned to a new state.

DETAILED DESCRIPTION

Referring to FIG. 1, an exemplary network traffic management system 10, which incorporates an exemplary network traffic management apparatus 12, is illustrated. In this example, the network traffic management apparatus 12 is coupled to a plurality of server devices 14(1)-14(n) and a plurality of client devices 16(1)-16(n) via communication network(s) 18, although the network traffic management apparatus 12, server devices 14(1)-14(n), and/or client devices 16(1)-16(n) may be coupled together via other topologies. Additionally, the network traffic management system 10 may include other network devices such as one or more routers and/or switches, for example, which are well 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 analyze TCP connections and associated state changes to facilitate improved TCP performance.

Referring to FIGS. 1-2, the network traffic management apparatus 12 of the network traffic management system 10 may perform any number of functions including managing network traffic, load balancing network traffic across the server devices 14(1)-14(n), and/or accelerating network traffic associated with applications hosted by the server devices 14(1)-14(n), for example. The network traffic management apparatus 12 in this example includes one or more processors 20, a memory 22, and/or a communication interface 24, which are coupled together by a bus 26 or other communication link, although the network traffic management apparatus 12 can include other types and/or numbers of elements in other configurations.

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 the any number of the functions identified above. The processor(s) 20 of the network traffic management apparatus 12 may include one or more 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 FIGS. 3-4. The application(s) can be implemented as modules or components of other applications. Further, the application(s) can be implemented as operating system extensions, module, plugins, or the like.

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 embodiments 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 includes a TCP monitor module 28 and a TCP statistics table 30, although the memory 22 can include other policies, modules, databases, tables, data structures, or applications, for example. The TCP monitor module 28 in this example is configured to monitor TCP connections with the client devices 16(1)-16(n) and/or server devices 14(1)-14(n). In particular, the TCP monitor module 28 is configured to identify state transitions associated with TCP connections and the duration that the network traffic management apparatus 12 is in each state, as described and illustrated in more detail later.

The TCP statistics table 30 in this example stores the duration associated with each state as well as a time of a previous transition for each monitored TCP connection. Optionally, the TCP statistics table 30 can facilitate reporting of the durations and/or transitions, which can be aggregated by entities and combined with an application visibility and reporting module of the network traffic management apparatus 12 storing additional performance information and/or statistics. Other information can also be stored in the TCP statistics table 30 and TCP state duration data can also be stored in other manners in other examples.

The communication interface 24 of the network traffic management apparatus 12 operatively couples and communicates between the network traffic management apparatus 12, the server devices 14(1)-14(n), and/or the client devices 16(1)-16(n), which are all coupled together by the communication network(s) 18, although other types and/or numbers of communication networks or systems with other types and/or numbers of connections and/or configurations to other devices and/or elements can also be used.

By way of example only, the communication network(s) 18 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 and/or numbers of protocols and/or communication networks can be used. The communication network(s) 18 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. The communication network(s) 18 can also include direct connection(s) (e.g., for when a device illustrated in FIG. 1, such as the network traffic management apparatus 12, one or more of the client devices 16(1)-16(n), or one or more of the server devices 14(1)-14(n) operate as virtual instances on the same physical machine).

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 standalone devices or integrated with one or more other devices or apparatuses, such as one 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 communication interface, 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 process requests received from the client devices 16(1)-16(n) via the communication network(s) 18 according to the HTTP-based application RFC protocol, for example. Various applications may be operating on the server devices and transmitting data (e.g., files or Web pages) to the client devices 16(1)-16(n) 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 a plurality of 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 and/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 the communication network(s). In this example, the one or more 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 send and receive packets using TCP connections via the communication network(s) 18, such as mobile computing devices, desktop computing devices, laptop computing devices, 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, although other numbers and/or types of network devices could 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. The client devices 16(1)-16(n) may further include a display device, such as a display screen or touchscreen, and/or an input device, such as a keyboard for example.

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 are described and illustrated herein, other types and/or numbers of systems, devices, components, and/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 traffic management system 10, such as the network traffic management apparatus 12, client devices 16(1)-16(n), or server devices 14(1)-14(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, client devices 16(1)-16(n), or server devices 14(1)-14(n) may operate on the same physical device rather than as separate devices communicating through communication network(s). Additionally, there may be more or fewer network traffic management apparatuses, client devices, or server devices than illustrated in FIG. 1. The client devices 16(1)-16(n) could also be implemented as applications on the network traffic management apparatus 12 itself as a further example.

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 teletraffic in any suitable form (e.g., voice and modem), 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 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, 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 facilitating improved TCP connection performance will now be described with reference to FIGS. 1-4. Referring more specifically to FIG. 3, an exemplary method for determining state durations in a TCP connection is illustrated. Although steps 300-314 are described and illustrated herein as being performed by the network traffic management apparatus 12 of the network traffic management system 10, one or more other devices of the network traffic management system 10, such as one or more of the client devices 16(1)-16(n) or server devices 14(1)-14(n), for example, can also perform one or more of steps 300-314 in other examples.

In step 300 in this example, the network traffic management apparatus 12 determines whether a new TCP connection has been initiated with a remote network device, such as one of the client devices 16(1)-16(n) or one of the server devices 14(1)-14(n), for example. In some examples, a synchronization packet or SYN message received by the network traffic management apparatus 12 can initiate a three way handshake and a new TCP connection. If the network traffic management apparatus 12 determines that a new TCP connection has not been initiated, then the No branch is taken back to step 300 and the network traffic management apparatus 12 effectively waits for a new TCP connection to be initiated. However, if the network traffic management apparatus 12 determines in step 300 that a new TCP connection has been initiated, then the Yes branch is taken to step 302.

In step 302 in this example, the network traffic management apparatus 12 determines whether an event has occurred with respect to the TCP connection. In some examples, the event can be one or more of sending a packet via the TCP connection, receiving data at the TCP stack from an upper layer, expiration of a TCP timer, or receiving a packet via the TCP connection, such as an acknowledgement packet or ACK message, although other types of events can be used in other examples. If the network traffic management apparatus 12 determines that an event has not occurred with respect to the TCP connection, then the No branch is taken back to step 302 and the network traffic management apparatus effectively waits for an event. However, if the network traffic management apparatus 12 determines in step 302 that an event has occurred with respect to the TCP connection, then the Yes branch is taken to step 304.

In step 304 in this example, the network traffic management apparatus 12 determines whether the event corresponds with a reset packet or RST message that has been sent or received, which indicates an end to the statistical data collection for the TCP connection, which is described and illustrated in more detail later. If the network traffic management apparatus 12 determines that the event is not the sending or receiving of an RST message, then the No branch is taken to step 306.

In step 306 in this example, the network traffic management apparatus 12 determines whether the event corresponds with an acknowledgement, by the remote network device associated with the TCP connection, of a finish packet or FIN message sent by the network traffic management apparatus. If a FIN message has been acknowledged by the remote network device, then the TCP connection is effectively closed, and the statistical data collection for the TCP connection, which is described and illustrated in more detail later, can be stopped. Accordingly, if the network traffic management apparatus 12 determines that the event is not the receiving of an acknowledgement of a sent FIN message, then the No branch is taken to step 308.

In step 308 in this example, the network traffic management apparatus determines whether the event corresponds with a transition to a new state in the TCP connection. One exemplary method for determining whether the TCP connection has transitioned to a new state is described and illustrated in more detail later with reference to FIG. 4. Exemplary states include three way handshake, rate pace, receive window, congestion window, send buffer, Nagle, retransmission, wait for acknowledgement, closing, and application states, although other numbers and types of states can be used in other examples.

If the network traffic management apparatus 12 determines that the TCP connection has not transitioned to a new state based on the event, then the No branch is taken back to step 302 and the network traffic management apparatus 12 again waits for another event to occur with respect to the TCP connection. However, in this particular example, if the network traffic management apparatus 12 determines in step 308 that the TCP connection has transitioned to a new state, then the Yes branch is taken to step 310. In other examples, the network traffic management apparatus 12 may exit step 308 based on a timer elapsing. In these examples, statistics can be generated, as described and illustrated in more detail later, even though state transition are not occurring.

In step 310 in this example, the network traffic management apparatus 12 generates a duration corresponding to a current state. In some examples, the duration is generated based on a difference between a stored time of a previous transition to the current state and a current time. Accordingly, the network traffic management apparatus 12 stores in the memory 22 a timestamp associated with an immediately prior state transition to a current state, which can be compared to a current time to determine a duration in which the TCP connection was in the current state before the TCP connection transitioned to the new state. The network traffic management apparatus 12 can store the generated duration in the TCP statistics table 30 along with an indication of the current state and, optionally, an indication of the TCP connection or one or more parameters associated with the TCP connection, for example.

In step 312, the network traffic management apparatus 12 replaces the stored time of the previous state transition with the current time so that in a subsequent iteration the network traffic management apparatus 12 can determine in step 310 a duration in which the TCP connection was in the new state. Subsequent to replacing the stored time of the previous state transition, the network traffic management apparatus 12 proceeds back to step 302 and again waits for a determination that an event has occurred with respect to the TCP connection.

Referring back to steps 304 and 306, if the network traffic management apparatus 12 determines that the event is the sending or receiving of an RST message or the receiving of an acknowledgement of a sent FIN message, respectively, then one of the Yes branches is taken to step 314. In step 314, the network traffic management apparatus 12 aggregates or reports durations for each of the states that the TCP connection was in while the TCP connection was open, which are maintained in the TCP statistics table 30.

Accordingly, the network traffic management apparatus 12 can aggregate the total time a TCP connection was in a particular state for states to which the TCP connection transitioned. In another example, the network traffic management apparatus can aggregate the duration statistics for a particular TCP connection with one or more other TCP connections associated with a same entity (e.g., geographic location or IP address of remote network device), such as by providing the duration statistics to an application, visibility, and reporting module of the network traffic management apparatus 12 for example.

In yet other examples, the network traffic management apparatus 12 can output the duration statistics to a file or other data structure that is accessible to an administrator, such as in response to a query via a provided interface. The duration statistics can also be aggregated or reported in different ways in other examples. While the duration statistics are aggregated or reported following the closing of a TCP connection in this example, the duration statistics can also be aggregated or reported at specified time intervals or at other times in other examples.

In step 316, the network traffic management apparatus 12 optionally determines whether a duration for any of the states exceeds a configurable threshold (e.g., percentage of total connection time for the TCP connection). In some examples, the network traffic management apparatus 12 can execute a daemon or other process that analyzes the accumulated durations for each state with respect to a stored policy of configurable thresholds. Accordingly, if the network traffic management apparatus 12 determines that a threshold is exceeded for at least one state, then the Yes branch is taken to step 318.

In step 318, the network traffic management apparatus 12 optionally modifies one or more TCP configurations automatically or based on a stored policy. In one particular example, the network traffic management apparatus 12 can disable Nagle's algorithm when the duration associated with the Nagle state for one or more TCP connections exceeds a configurable threshold of 5% of the total connection time for the TCP connection(s). Other types of thresholds, policies, and automated modifications to the TCP configuration(s) can also be used in other examples.

Subsequent to modifying the TCP configuration(s), or if the network traffic management apparatus 12 determines in step 316 that a threshold is not exceeded for any of the states and the No branch is taken, then the network traffic management apparatus 12 proceeds back to step 300. Additionally, steps 302-318 can be performed in parallel for any number of TCP connections in other examples.

Referring more specifically to FIG. 4, an exemplary method for determining whether a TCP connection has transitioned to a new state is illustrated. While FIG. 4 illustrates a plurality of exemplary monitored states for which durations can be determined, any number of states can be monitored in a TCP connection in other examples. Additionally, FIG. 4 illustrates an exemplary order in which state transitions are analyzed, although the conditions for a state transition can be analyzed in other orders in other examples. Although steps 400-442 are described and illustrated herein as being performed by the network traffic management apparatus 12, one or more other devices of the network traffic management system 10, such as one or more of the client devices 16(1)-16(n) or server devices 14(1)-14(n), for example, can also perform one or more of steps 400-442 in other examples.

In step 400 in this example, the network traffic management apparatus 12 determines whether an ACK message has been received from a remote network device in response to a SYN message sent to the remote network device. The remote network device in this example can be one of the client devices 16(1)-16(n), one of the server devices 14(1)-14(n) or any other network device within or external to the network traffic management system 10. If the network traffic management apparatus 12 determines that it has not received an ACK message from a remote network device in response to a SYN message, then the No branch is taken to step 402.

In step 402, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a three way handshake state. In this example, the three way handshake is an initial state, which cannot be transitioned to from any other state. Accordingly, the network traffic management apparatus 12 can set or store an initial time of transition to the three way handshake based on a current time, which can be used to determine the duration the TCP connection is in the three way handshake state, as described and illustrated in more detail earlier with reference to steps 310-312.

However, if the network traffic management apparatus 12 determines in step 400 that it has received an ACK message from a remote network device in response to a SYN message sent to the remote network device, then the Yes branch is taken to step 404. In step 404, the network traffic management apparatus 12 determines whether the most recent sent packet is not associated with the highest sequence number that has been observed for the TCP connection.

In this example, the network traffic management apparatus 12 maintains, such as in the memory 22, an indication of the sequence number that have been used in the context of the TCP connection. Accordingly, if the network traffic management apparatus 12 determines that a sent packet is not associated with a highest sequence number, then the sent packet is a retransmission and the No branch is taken to step 406. In step 406, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a retransmission state.

However, if the network traffic management apparatus 12 determines in step 404 that the most recent sent packet is associated with the highest sequence number that has been observed for the TCP connection, then the Yes branch is taken to step 408 and, optionally, the stored highest sequence number is incremented. In step 408, the network traffic management apparatus 12 determines whether it has sent all available data or whether there is data waiting in the memory 22 to be sent via the TCP connection to the remote network device. If the network traffic management apparatus 12 determines that all available data has been sent, then the Yes branch is taken to step 410.

In step 410, the network traffic management apparatus 12 determines whether all of the data sent to the remote network device has been acknowledged. If the network traffic management apparatus 12 determines that all of the data has been acknowledged, then the Yes branch is taken to step 412. In step 412, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a wait for acknowledgement state. However, if the network traffic management apparatus 12 determines in step 410 that all of the data sent to the remote network device has not been acknowledged, then the No branch is taken to step 414.

In step 414, the network traffic management apparatus 12 determines whether a FIN message has been sent to the remote network device. If all of the data sent to the remote network device has been acknowledged, but a FIN message has not been sent, then the network traffic management apparatus 12 is waiting for additional data, such as from an upper layer or an application.

Accordingly, if the network traffic management apparatus 12 determines that a FIN message has been sent, then the Yes branch is taken to step 416. In step 416, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a closing state, indicating that the network traffic management apparatus 12 is waiting on an acknowledgement of the FIN message and for the TCP connection to close. If the FIN message has been acknowledged, then the network traffic management apparatus 12 does not determine whether the TCP connection has transitioned to a new state based on the analysis of FIG. 4, as described and illustrated in more detail earlier with reference to step 306 of FIG. 3.

However, if the network traffic management apparatus 12 determines in step 414 that a FIN message has not been sent to the remote network device, then the No branch is taken to step 418. In step 418, the network traffic management apparatus 12 determines that the TCP connection is transitioning to an application state indicating that the network traffic management apparatus 12 is waiting on an application for more data.

Referring back to step 408, if the network traffic management apparatus 12 determines that all available data has not been sent, then the No branch is taken to step 420. In step 420, the network traffic management apparatus 12 updates a stored flight size based on a size of the data sent to the remote network device, but not yet acknowledged by the remote network device. The current flight size associated with the TCP connection, as well as the current total size of data sent but unacknowledged, can be stored in the memory 22 of the network traffic management apparatus 12, for example.

In step 420, the network traffic management apparatus 12 determines whether the flight size is less than one maximum segment size (MSS) below the last advertised receive window of the remote network device. If the network traffic management apparatus 12 determines that the flight size is less than one maximum segment size below the last advertised receive window of the remote network device, then the Yes branch is taken to step 424. In step 424, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a receive window state.

However, if the network traffic management apparatus 12 determines in step 422 that the flight size is not less than one maximum segment size (MSS) below the last advertised receive window (RWND) of the remote network device, then the No branch is taken to step 426. In step 426, the network traffic management apparatus 12 determines whether the flight size is less than one maximum segment size below a maximum send buffer size for the TCP connection.

If the network traffic management apparatus 12 determines that the flight size is less than one maximum segment size below a maximum send buffer size for the TCP connection, then the Yes branch is taken to step 428. In step 428, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a send buffer state.

However, if the network traffic management apparatus 12 determines in step 426 that the flight size is not less than one maximum segment size below a maximum send buffer size for the TCP connection, then the No branch is taken to step 430. In step 430, the network traffic management apparatus 12 determines whether the flight size is less than one maximum segment size below a size of a current congestion window for the TCP connection, such as can be determined by a congestion control algorithm that is currently implemented for the TCP connection.

If the network traffic management apparatus 12 determines that the flight size is less than one maximum segment size below the size of the current congestion window for the TCP connection, then the Yes branch is taken to step 432. In step 432, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a congestion window state.

However, if the network traffic management apparatus 12 determines in step 430 that the flight size is not less than one maximum segment size below a size of a current congestion window for the TCP connection, then the No branch is taken to step 434. In step 434, the network traffic management apparatus 12 determines whether the Nagle algorithm is enabled and there is unsent data in memory of less than one maximum segment size.

If the network traffic management apparatus 12 determines that the Nagle algorithm is enabled and there is unsent data in the memory 22 of less than one maximum segment size, then the Yes branch is taken to step 436. In step 436, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a Nagle state.

However, if the network traffic management apparatus 12 determines in step 434 that use of a Nagle algorithm is not enabled or there is not unsent data in the memory 22 of less than one maximum segment size then the No branch is taken to step 438. In step 438, the network traffic management apparatus 12 determines whether there is an active process limiting the rate at which packets exit in order to conform to link bandwidth and there is unsent data in the memory 22.

If the network traffic management apparatus 12 determines that there is an active process limiting the rate at which packets exit in order to conform to link bandwidth and there is unsent data in the memory 22, then the Yes branch is taken to step 440. In step 440, the network traffic management apparatus 12 determines that the TCP connection is transitioning to a rate pace state.

However, if the network traffic management apparatus 12 determines in step 438 that there is an active process limiting the rate at which packets exit in order to conform to link bandwidth or there is no unsent data in the memory 22, then the No branch is taken to step 442. In step 442, the network traffic management apparatus 12 determines that the TCP connection is not transitioning states.

Accordingly, in this particular example, steps 400-442 are performed by the network traffic management apparatus 12 for each determination of an event, as described and illustrated earlier with reference to step 302 of FIG. 3, for which the conditions described and illustrated earlier with reference to steps 304 and 306 of FIG. 3 are not satisfied. Other types and numbers of conditions or states or other methods of determining whether a state transition has occurred in a TCP connection can also be used in other examples.

By generating and providing statistics regarding the duration that TCP connection(s) are in particular states, network administrators can more effectively identify the delays that may be occurring in the TCP connection(s). Additionally, by identifying the types of delays and associated durations, administrators can advantageously adjust, and/or network traffic management apparatuses can automatically adjust, TCP configuration(s) in order to reduce the delays (e.g., disable the Nagle algorithm), and thereby improve TCP performance.

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.

Claims

1. A method for improved transmission control protocol (TCP) performance implemented by a network traffic management system comprising one or more network traffic management apparatuses, client devices, or server devices, and the method comprising: monitoring a TCP connection to determine when an event and a current transition from a previous state to a new state have occurred in the TCP connection and, when the determination indicates that the event and the current transition from the previous state to the new state have occurred in the TCP connection: generating a duration corresponding to the previous state;determining, based on the generated duration, when one or more TCP configurations require modification; andautomatically modifying the one or more TCP configurations to improve TCP performance, when the determination indicates that the one or more TCP configurations require modification.

2. The method of claim 1, further comprising: generating the duration based on a difference between a stored time recorded at a previous transition to the previous state and a current time of the current transition; andreplacing the stored time with the current time.

3. The method of claim 1, wherein the event comprises one or more of sending a packet, receiving data from an upper layer, expiration of a TCP timer, or receiving another packet comprising an acknowledgement.

4. The method of claim 1, further comprising storing or outputting the generated duration as associated with the previous state.

5. The method of claim 1, further comprising: determining when a reset packet has been received or an acknowledgement packet has been received in response to a finish packet; andoutputting the stored duration or another stored duration corresponding to one or more other states, when the determination indicates that the reset packet has been received or the acknowledgement packet has been received in response to the finish packet.

6. A network traffic management apparatus, comprising memory comprising programmed instructions stored thereon and one or more processors configured to be capable of executing the stored programmed instructions to: monitor a TCP connection to determine when an event and a current transition from a previous state to a new state have occurred in the TCP connection and, when the determination indicates that the event and the current transition from the previous state to the new state have occurred in the TCP connection: generate a duration corresponding to the previous state;determine, based on the generated duration, when one or more TCP configurations require modification; andautomatically modify the one or more TCP configurations to improve TCP performance, when the determination indicates that the one or more TCP configurations require modification.

7. The network traffic management apparatus of claim 6, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to: generate the duration based on a difference between a stored time recorded at a previous transition to the previous state and a current time of the current transition; andreplace the stored time with the current time.

8. The network traffic management apparatus of claim 6, wherein the event comprises one or more of sending a packet, receiving data from an upper layer, expiration of a TCP timer, or receiving another packet comprising an acknowledgement.

9. The network traffic management apparatus of claim 6, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to store or output the generated duration as associated with the previous state.

10. The network traffic management apparatus of claim 6, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to: determine when a reset packet has been received or an acknowledgement packet has been received in response to a finish packet; andoutput the stored duration or another stored duration corresponding to one or more other states, when the determination indicates that the reset packet has been received or the acknowledgement packet has been received in response to the finish packet.

11. A non-transitory computer readable medium having stored thereon instructions for improved transmission control protocol (TCP) performance comprising executable code which when executed by one or more processors, causes the one or more processors to: monitor a TCP connection to determine when an event and a current transition from a previous state to a new state have occurred in the TCP connection and, when the determination indicates that the event and the current transition from the previous state to the new state have occurred in the TCP connection: generate a duration corresponding to the previous state;determine, based on the generated duration, when one or more TCP configurations require modification; andautomatically modify the one or more TCP configurations to improve TCP performance, when the determination indicates that the one or more TCP configurations require modification.

12. The non-transitory computer readable medium of claim 11, wherein the executable code when executed by the one or more processors further causes the one or more processors to: generate the duration based on a difference between a stored time recorded at a previous transition to the previous state and a current time of the current transition; andreplace the stored time with the current time.

13. The non-transitory computer readable medium of claim 11, wherein the event comprises one or more of sending a packet, receiving data from an upper layer, expiration of a TCP timer, or receiving another packet comprising an acknowledgement.

14. The non-transitory computer readable medium of claim 11, wherein the executable code when executed by the one or more processors further causes the one or more processors to store or output the generated duration as associated with the previous state.

15. The non-transitory computer readable medium of claim 11, wherein the executable code when executed by the one or more processors further causes the one or more processors to: determine when a reset packet has been received or an acknowledgement packet has been received in response to a finish packet; andoutput the stored duration or another stored duration corresponding to one or more other states, when the determination indicates that the reset packet has been received or the acknowledgement packet has been received in response to the finish packet.

16. A network traffic management system, comprising one or more traffic management apparatuses, client devices, or server devices, memory comprising programmed instructions stored thereon, and one or more processors configured to be capable of executing the stored programmed instructions to, when a determination indicates that an event and a current transition from a previous state to a new state have occurred in a monitored transmission control protocol (TCP) connection: generate a duration corresponding to the previous state; andautomatically modify one or more TCP configurations to improve TCP performance, when a determination based on the generated duration indicates that the one or more TCP configurations require modification.

17. The network traffic management system of claim 16, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to: generate the duration based on a difference between a stored time recorded at a previous transition to the previous state and a current time of the current transition; andreplace the stored time with the current time.

18. The network traffic management system of claim 16, wherein the event comprises one or more of sending a packet, receiving data from an upper layer, expiration of a TCP timer, or receiving another packet comprising an acknowledgement.

19. The network traffic management system of claim 16, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to store or output the generated duration as associated with the previous state.

20. The network traffic management system of claim 16, wherein the one or more processors are further configured to be capable of executing the stored programmed instructions to output the stored duration or another stored duration corresponding to one or more other states, when a determination indicates that a reset packet has been received or an acknowledgement packet has been received in response to a finish packet.