KR101309869B1 - Method of switching ethernet lpi mode - Google Patents

Abstract

The present invention discloses an Ethernet mode conversion method. The present invention provides an energy efficient Ethernet mode conversion method, the method comprising: waiting for a predetermined waiting time when the transmission of the packet is completed in the activation mode, and using the received packet when the amount of the received packet is greater than the maximum receiving amount. Calculating a predicted packet reception amount to be received, and comparing the calculated amount of received packets during the predetermined waiting time with the calculated predicted packet reception amount, and switching an Ethernet mode according to the comparison result. . Accordingly, the present invention can maximize the energy efficiency and transmission efficiency of an Ethernet link while optimizing the performance of TCP using a cross-layer technique in Ethernet.

Description

How to switch Ethernet LPI mode {METHOD OF SWITCHING ETHERNET LPI MODE}

The present invention relates to an Ethernet mode, and more particularly to a method of switching LPI mode of energy-efficient Ethernet.

Ethernet is the most commonly used networking technology in local area networks (LANs) and is a networking technology that operates on a network that connects multiple PCs, such as laptops, desktops, and server computers. Ethernet is widely used in homes and commercial districts and is the most widely deployed subscriber network networking technology in the world.

This network environment continuously transmits idle signals to maintain alignment between transmitter and receiver even when there is no data to transmit, so most components of the network card are always active and consume unnecessary power. It is observed to consume about 6 TWh (Tera Watt hours) power.

For this reason, the IEEE 802.3az Working Group has standardized on energy efficient solutions to address the corresponding costs of using IT equipment such as PCs, display devices, printers, servers, and network equipment. As a result, the IEEE 832.3az Working Group adopted the standard based on the Low Power Idle (LPI) mode and specified the detailed operation of the physical layer to support it.

However, the detailed operation of the LPI Client sublayer is not specified, and research on the optimal mechanism has emerged as an important issue.

An object of the present invention for solving the above problems is to provide an Ethernet mode switching method according to the presence or absence of packets.

Ethernet mode switching method according to an embodiment of the present invention for achieving the above object of the present invention, the step of waiting for a predetermined waiting time when the transmission of the packet in the activation mode, the amount of packets received during the waiting maximum Calculating a predicted packet reception amount to be received during a predetermined waiting time using the received packet when the amount is larger than the received amount, comparing the amount of packets received during the predetermined waiting time with the calculated predicted packet reception amount, and comparing the result The method may include switching a mode of Ethernet.

The calculating of the prediction packet reception amount may include calculating a congestion window until the amount of the received packet is greater than a maximum reception amount when the predetermined waiting time ends, and calculating the prediction packet reception amount using the congestion window. The congestion window may be a frame for determining the amount of packets that can be transmitted to the receiving end.

The mode switching of the Ethernet may be switched to the activation mode when the amount of the received packet is larger than the predicted packet reception amount before the predetermined waiting time ends.

In the mode switching of the Ethernet, the amount of received packets is smaller than the calculated predicted packet receiving amount, and when the predetermined waiting time ends, the mode may be switched from the active mode to the inactive mode.

By using the Ethernet mode switching method according to the present invention as described above, it is possible to maximize the energy efficiency and transmission efficiency of the Ethernet link while optimizing the performance of TCP using a cross-layer technique in Ethernet.

1 is a sequence chart illustrating an operation procedure of a low power idle mode (LPI).
2 is a diagram illustrating the detailed operation of the physical layer to support the interface between the RS layer and the LPI client sublayer and LPI mode.
3 is a graph for explaining the change in the congestion window size of slow start and congestion avoidance.
4 is a diagram illustrating an interface between an LPI client and a TCP layer.
5 is a flowchart illustrating an Ethernet mode switching method according to an embodiment of the present invention.
6 is a diagram illustrating an Ethernet mode switching algorithm according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described with reference to the accompanying drawings. It is to be noted that the same components of the drawings are denoted by the same reference numerals and symbols as possible even if they are shown in different drawings. In the following description of the present invention, if it is determined that a detailed description of a related known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted.

Also, when an element is referred to as "comprising ", it means that it can include other elements as well, without departing from the other elements unless specifically stated otherwise.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

An ethernet mode switching method for performing energy efficient ethernet (EEE) will be substantially shown or described in connection with at least one of the figures and will be more fully developed in the claims.

Ethernet is being applied in a variety of environments (eg, twisted pairs, backplanes, etc.) and is becoming an increasingly compelling technology. IEEE 802.3az Energy Efficient Ethernet evaluates various ways to reduce energy used during periods of low link utilization. In this process, a protocol may be defined that facilitates the transition from / to low power consumption modes according to changes in network requirements.

Low Power Idle (LPI) relies on switching from active mode to inactive mode when not transmitting. Energy is thereby saved when the link is off. Refresh signals may be sent periodically to switch from inactive mode to active mode.

In one embodiment, a synchronization signal on the interfaces (i.e. medium dependent interface (MDI) and PHY / MAC interface) to quickly switch from inactive mode to active mode and maintain frequency lock. Can be used.

1 is a sequence chart illustrating an operation procedure of a low power idle mode (LPI).

Referring to FIG. 1, the LPI mode may include an activation mode, an inactivation mode, and a refresh mode. In this case, when there is a packet to be transmitted from the transmitting end to the receiving end, the transmitting end may transmit the packet to the receiving end in the activation mode.

In addition, in the activating mode, when the transmitting end completes packet transmission and there is no data to transmit to the receiving end, the transmitting end is switched from the activating mode to the deactivating mode. In order to maintain synchronization between the transmitting end and the receiving end, the transmitting end may transmit the refresh signal to the receiving end in the refresh mode.

Although the sustain periods of the activation mode, the deactivation mode, and the refresh mode are arbitrarily defined in FIG. 1, the retention periods of the activation mode, the deactivation mode, and the refresh mode are respectively defined according to the state of the network and the reception rate of data received in the buffer in the deactivation mode. It should be noted that this may be changed, so that FIG. 1 may be changed accordingly.

When the transmitting end receives the packet from the upper layer in the inactive mode, the LPI mode is switched from the inactive mode to the active mode at the time T1 after the Tw period. The transmitting end may transmit the packet to the receiving end from the time T1 at which the activation mode begins to the time T2 at which the activation mode ends.

In the activating mode, when the transmitting end completes the packet transmission and there is no data to transmit to the receiving end, the LPI mode is changed from the activating mode to the inactive mode after the Ts period from the time point T2 to maintain the inactive mode.

In this case, the transmitting end may transmit the packet to the receiving end in an interval from the time T1 at which the activation mode is started to the time T2 at which the deactivation mode is switched, and thus may be called an active period.

In addition, in the inactive mode, the transmitting end does not transmit data to the receiving end, but the transmitting end must maintain synchronization with the receiving end. To this end, the LPI mode switches from the inactive mode to the refresh mode at the time T3 after the Ts period, for example, at the time T4 after the Tq period, thereby maintaining the refresh mode.

In the refresh mode, the transmitting end transmits a refresh signal to the receiving end to maintain synchronization with the receiving end. When the transmitting end completes the transmission of the leaflay signal in the refresh mode, the LPI mode is switched from the refresh mode to the inactive mode.

When the packet is received from the upper layer in the deactivation mode, the LPI mode is switched from the deactivation mode to the activation mode at the time T5 after the Tw period. In the inactive mode, the transmitting end may transmit the packet to the receiving end.

In the activating mode, when the transmitting end completes packet transmission and there is no data to transmit to the receiving end, the LPI mode is changed from the activating mode to the inactive mode after the Ts period from the time point T6 to maintain the inactive mode.

As described above, in the deactivation mode, in the deactivation mode, the transmitting end does not transmit data to the receiving end, but the transmitting end transmits a refresh signal to maintain synchronization with the receiving end. In addition, upon receiving a packet from a higher layer in the inactive mode, the LPI mode is switched from the inactive mode to the active mode.

That is, as described above, the LPI mode may be switched to an activation mode, an inactive mode, and a refresh mode according to the presence or absence of a packet.

Meanwhile, overhead may be added when the LPI mode is switched from the inactive mode to the inactive mode. This overhead means a Tw period for switching from inactive mode to active mode and a Ts period for switching from active mode to inactive mode.

If the LPI mode attempts to switch from the active mode to the inactive mode, if a packet is received during the Ts period required to switch to the inactive mode, the LPI mode is not switched from the active mode to the inactive mode and remains in the active mode.

However, when switching from the active mode to the inactive mode and the inactive mode to the active mode depending only on the presence or absence of the packet, mode switching may frequently occur in a network in which the packet reception rate is low, which may cause an overhead problem.

In order to solve this problem, two conditions for switching from inactive state to active state have been proposed. First, the transmit end may be an amount of received packets from a higher layer for a predetermined waiting time for the LPI mode to switch from the active mode to the inactive mode.

For example, in a network with a high rate of packet reception, the transmitting end does not take long for the amount of packets received from the upper layer in the deactivation mode to exceed a certain threshold value?. In this case, when the amount of packets exceeds a certain threshold value?, The activation mode can be maintained without switching to the inactive mode, so that the energy efficiency is maximized.

Secondly, there may be a predetermined waiting time for the LPI mode to switch from the activation mode to the deactivation mode. For example, in a network where the packet reception rate is low, the transmitting end takes a long time when the amount of packets received from the upper layer in the deactivation mode exceeds a certain threshold value?.

In this case, the energy efficiency is maximized because the amount of packets does not exceed the specific threshold value?, But the switch to the inactive mode when the predetermined waiting time ends.

However, in a network where the packet reception rate is low, it may take a long time for the amount of packets received from the upper layer to be above a certain threshold value τ by a transmitting end. Rather, energy efficiency is not good.

Alternatively, in a network with a high packet reception rate, it may not take a long time for the amount of packets received from the upper layer to exceed a certain threshold τ, but if the amount of packets is short until a predetermined waiting time for switching to inactive mode. There may be a disadvantage that the predetermined dash time ends before the specific threshold value τ or more is switched to the inactive mode.

Therefore, by limiting the predetermined waiting time of the packet, for example, the maximum delay time to the variable Tmax, the delay of the packet can be mitigated.

As described above, in the switching of the LPI mode, first, the amount of packets to be received by the transmitting end from the upper layer during a predetermined waiting time for the LPI mode from the active mode to the inactive mode, and second, the LPI mode is switched from the active mode to the inactive mode. It is a predetermined waiting time to become.

Both conditions are related to the delay of the packet, and increasing the packet delay leads to an increase in the Round Trip Time (RTT) value. The RTT value has a significant impact on the performance of TCP traffic, and may represent a difficulty in guaranteeing the quality of service, which is a very important factor in processing real-time multimedia traffic based on the Internet.

2 is a diagram illustrating the detailed operation of the physical layer to support the interface between the RS layer and the LPI client sublayer and LPI mode.

Referring to FIG. 2, a MAC layer may exist in an upper layer of a reconciliation sublayer (RS) layer, and a physical layer may exist in a lower layer. The RS layer is a layer that converts signals so that the MAC layer can perform communication regardless of the physical layer.

For example, the RS layer converts data received from the physical layer into physical layer signaling (PLS) primitives so that the MAC layer can recognize the data, or transmits data from the MAC layer according to the type of link. It is a hierarchy that can be converted.

By arranging the LPI Client sublayer above the RS layer, the RS layer converts signals so that the LPI Client sublayer can communicate regardless of the physical layer.

3 is a graph for explaining the change in the congestion window size of slow start and congestion avoidance.

Referring to FIG. 3, when receiving a plurality of packets having the same ACK sequence number, the transmitter assumes that the packet is lost during transmission and retransmits the lost packet. If the retransmission packet is lost or damaged during transmission, the transmitting end does not receive an ACK packet indicating that the retransmitted packet has been received from the receiving end, and thus cannot transmit for a predetermined time until the retransmission timer expires.

As a result, when the transmission time increases and the retransmission timer expires, the transmitting end performs a slow start. In the slow start state, the window is exponentially increased by the ACK packet received from the receiving end.

Therefore, if we measure the time and congestion window starting from the first packet received during Ts until n packets arrive, we can predict how many packets arrive during Tmax and calculate the average packet arrival rate based on this. have.

However, the congestion window value is often larger than the MAC buffer size. Therefore, if the ssthresh value is obtained from TCP and the ratio is calculated and applied to TCP, mode conversion can be efficiently performed. However, when a certain amount of the TCP buffer is maintained, the active mode is always maintained. Therefore, the result value must be limited to the MAC buffer size so that an appropriate mode switch can be performed.

In other words, TCP congestion avoidance starts when the congestion window increases exponentially at the slow start to equal the ssthresh value. In the TCP congestion avoidance state, the value of the congestion window is increased by 1 for one ACK received from the receiver.

The value of ssthresh is set to the size / 2 of the congestion window. Here, the value of ssthresh is determined as half of the current latitude, which means that the maximum size of the approximate window where packet loss does not occur is 1.

The congestion window is also an element of the TCP congestion control algorithm that affects the size of the segment to be transmitted in SLOW START, CONGESTION AVOIDANCE, and FAST RECOVERY. This means that the specific limit value τ fluctuates depending on the network condition. Therefore, it is necessary to define the interaction between the LPI mechanism and the TCP congestion control mechanism.

4 is a diagram illustrating an interface between an LPI client and a TCP layer.

Referring to FIG. 4, each layer generally communicates with a layer existing in an upper layer or a lower layer to perform data transmission / reception. For example, the physical layer performs power control, and the RS layer may transmit state information about power of a device existing in an upper layer, an LPI client, or a MAC layer to a lower layer physical layer, so that the physical layer may RS It is possible to control the power of the device existing in the upper layer of the layer.

In the present invention, the LPI client is congested until the amount of packets reaches the maximum reception amount when the amount of packets received during the predetermined waiting time before the transition from the active state to the inactive state is greater than the maximum reception amount or when the predetermined waiting time ends. The window is calculated, and the estimated packet reception amount to be received for a predetermined waiting time is calculated using the calculated congestion window. Here, the LPI client should calculate the predicted packet reception amount by receiving information on the congestion window determined according to the network environment in the TCP layer.

However, in FIG. 4, since the LPI client is not directly above or below the TCP layer, the LPI client cannot receive information about a congestion window from the TCP layer. This is because each layer is generally able to transmit / receive data from the upper layer or lower layer.

To this end, in the present invention, the LPI Client can receive the information on the congestion window from the TCP layer through the cloth layer method.

5 is a flowchart illustrating an Ethernet mode switching method according to an embodiment of the present invention. In the embodiment of FIG. 5, when the transmitting end completes the transmission of the packet in the activation mode, the transmitter waits for a predetermined waiting time, for example, Ts in FIG.

At this time, while the transmitting end waits for a predetermined waiting time, the prediction packet reception amount to be received from the upper layer is calculated, and the amount of packets actually received is compared with the estimated packet reception amount calculated in advance. Can be maintained and can be switched from an active mode to an inactive mode.

Referring to FIG. 5, the transmitting end transmits the packet to the receiving end in the activation mode, and waits for a predetermined waiting time when the transmission of the packet is completed (S510). The transmitting end calculates a prediction packet reception amount to be received in the upper layer during the predetermined waiting time by using the transmission target data received from the upper layer during the predetermined period of time (S520).

For example, when the transmitting end receives the first packet from the upper layer, it starts the Tmere Ts measuring a predetermined waiting time, and if the transmitting end receives the second packet, the transmitting end increases the Ccount which counts the number of packets.

If the transmitter receives the packet until the Ts timer is completed or until Ccount reaches the Cmax value, which is the maximum number of reception of the mixed window. When the Ts timer is completed or Ccount reaches the Cmax value, the transmitting end calculates the predicted packet reception amount sτ of the packet to be received during Ts.

The transmitter calculates the maximum amount of packets that can be received for a predetermined dash time, and when the predetermined waiting time ends (S530), calculates a congestion window until the amount of received packets is greater than the maximum amount of reception (S540). The predicted packet reception amount is calculated using the window (S550). Here, the congestion window means a frame for determining the amount of packets that can be transmitted to the receiving end.

The transmitter calculates the maximum amount of packets that can be received during the predetermined waiting time for switching from the activation mode to the inactive mode, and then compares the amount of received packets with the maximum packet amount during the predetermined waiting time (S560). If the amount of the received packet is larger than the predicted packet reception amount (S570), it is switched to the activation mode (S580). On the other hand, although the amount of the received packet is not larger than the predicted packet reception amount (S570), when the predetermined waiting time is finished (S590), the mode is switched to the inactive mode (S500).

6 is a diagram illustrating an Ethernet mode switching algorithm according to an embodiment of the present invention.

Referring to FIG. 6, when the transmitting end receives a packet from an upper layer in an inactive state, the transmitter starts a timer Tmax for waiting for a predetermined waiting time and increases a variable Ccount that counts the number of times of receiving the packet. In addition, the transmitting end increases the value of the congestion window, which is the maximum value of the maximum reception amount of the packet to be received during the predetermined waiting time.

When the packet received from the upper layer reaches the maximum reception amount or the predetermined waiting time is completed, the transmitting end calculates a congestion window until the packet reception amount reaches the maximum reception amount. Since the calculated congestion window is too large, the transmitting end calculates the total predicted packet reception amount for Qsize using the ratio between ssthrd and Qsize described in FIG.

The present invention has been described with reference to preferred embodiments. Although specific terms have been employed herein, they are used for purposes of illustration only and are not intended to limit the scope of the invention as defined in the claims or the claims.

Therefore, it will be understood by those skilled in the art that the present invention may be implemented in a modified form without departing from the essential features of the present invention. Accordingly, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

Claims (4)

In the method of switching between the activation mode and deactivation mode of the Ethernet LPI mode,
In the activation mode, the transmitting end completes the transmission of the packet to the receiving end and waits for a predetermined waiting time;
The transmitting end calculates the maximum amount of packets to be received in the upper layer during the predetermined waiting time by using the transmission target data received from the upper layer during the predetermined period of the predetermined waiting time, and the amount of packets received during the predetermined waiting time is calculated. When the amount of the packet exceeds the maximum amount of packets or the end of the predetermined waiting time, information on the congestion window is received from the TCP layer through a cross-layer technique. Calculating a predicted packet reception amount to be received during a predetermined waiting time using time until n packets arrive at a start; And
Comparing, by the transmitter, an amount of packets actually received for a predetermined waiting time with the calculated amount of predicted packet reception, and switching the LPI mode of Ethernet according to the comparison result; Ethernet LPI mode switching method comprising a. The method of claim 1,
The congestion window is Ethernet LPI mode switching method characterized in that the frame for determining the amount of packets that can be transmitted to the receiving end. The method of claim 1,
The switching of the LPI mode of the Ethernet at the transmitting end may include switching to the active mode when the amount of the received packet is greater than the estimated packet reception amount before the predetermined waiting time ends. Way. The method of claim 1,
The switching of the LPI mode of the Ethernet at the transmitting end may include switching from the activation mode to the deactivation mode when the amount of received packets is smaller than the calculated predicted packet reception amount and the predetermined waiting time ends. How to switch Ethernet LPI mode.

Images