WO2019164426A1

WO2019164426A1 - Method and first node for selecting second node for transmission of indirect probe message to third node

Info

Publication number: WO2019164426A1
Application number: PCT/SE2018/050172
Authority: WO
Inventors: Xuejun Cai; Mina SEDAGHAT; Wolfgang John; Joacim Halén
Original assignee: Telefonaktiebolaget Lm Ericsson (Publ)
Priority date: 2018-02-22
Filing date: 2018-02-22
Publication date: 2019-08-29

Abstract

A method and a first node (110) for selecting a second node (120) for transmission of an indirect probe message for detection of failure of a third node (130) are disclosed. The first node (110) selects the second node (120) based on information about topology of the network (100). The first node (110) sends, to the second node (120), a request for instructing the second node (120) to transmit the indirect probe message towards the third node (130). Corresponding computer program(s) and computer program carrier(s) are also disclosed.

Description

METHOD AND FIRST NODE FOR SELECTING SECOND NODE FOR TRANSMISSION OF INDIRECT PROBE MESSAGE TO THIRD NODE.

TECHNICAL FIELD

Embodiments herein relate to failure detection in a node of a network, such as a computer network, a communication network, a core network of a mobile communication system or the like. In particular, a method and a first node for selecting a second node for transmission of an indirect probe message for detection of failure of a third node are disclosed. A corresponding computer program and a computer program carrier are also disclosed.

BACKGROUND

In order to make failure detection less dependent on a single node, distributed failure detection systems have been proposed. In this manner, the failure detection system avoids, at least to some extent, the problem of having a Single Point of Failure (SPF). Distributed failure detection systems are further well suited for other distributed systems, like cloud infrastructure, grid computing peer-to-peer systems and the like. In these kinds of systems, the distributed detection system is used to monitor a health status of each node and to detect potential failure of each node. In order to ensure consistency and to provide reliable applications/services on top of e.g. the cloud infrastructure, it is vital to have a good failure detection system that can fulfill requirements like high accuracy, high reliability, lightweight as in requiring a small amount of computational and/or memory resource for its operation and short detection time.

In general, failure detection is performed by exchange of so called keep-alive messages between the nodes in a distributed system. There are two types of keep-alive messages: heartbeat messages and polling messages.

A heartbeat message is sent, with a certain periodicity, from a monitored node to a failure detecting node in order to inform the detecting node about that the monitored node is still alive. The periodicity is known to both the monitored node and the failure detecting node. If the heartbeat message does not arrive at the failure detecting node according the periodicity, the failure detecting node suspects that the monitored node is faulty, or has failed. A polling message is sent from the failure detecting node to the monitored node. If no reply to the polling message is received, by the failure detecting node, before a timeout expires, the failure detecting node suspects that the monitored node is faulty. The polling message can be exemplified by an ICMP Ping message.

In for example a cloud infrastructure, network connectivity is thought of as an unreliable resource. In the cloud infrastructure, it is therefore difficult to distinguish if a monitored node failed or if the keep-alive message was lost due to failure in the network connectivity, such as a network congestion. Therefore, so called indirect probing has been introduced. With indirect probing, it is intended to reduce false detection rates caused by e.g. network congestion or the like.

In a known distributed failure detection system, described in“SWIM: Scalable Weakly-consistent Infection-Style Process Group Memebership Protocol”, by A. Das, I. Gupta, and A. Motivala, published in in Proceedings of the 2002 International

Conference on Dependable Systems and Networks, 2002, pp. 303-312, is illustrated in Figure 1. After every T time units, a node Mi selects a random node from its membership list, e.g., Mj, and sends a ping to it. It then waits for an ack message from Mj. If it does not receive the ack within the pre-specified timeout, Mi indirectly probes Mj by randomly selecting k nodes from its neighbors and asks them to send a ping to Mj. Each of these k nodes then sends a ping to Mj on behalf of Mi and on receiving an ack notifies Mi. If, for some reason, none of these processes receive an ack, Mi declares Mj as failed and notifies other neighbors.

It can be seen that after a node Mj failed to reply to a direct probe message, the probing node will ask other neighbors to send indirect probe message to the suspected node. Therefore, it can reduce the false detection alarm if the non-response from Mj is caused by the unreliable network between Mi and Mj. However, in some cases it may not reduce the false alarm.

To conclude, with existing failure detection systems, a disadvantage is that it is often difficult to distinguish whether a node failed or the probe message was lost due to network congestion, i.e. the keep-alive message has been discarded somewhere due to buffer overflow or the like.

It is intended to mitigate this disadvantage with indirect probing. However, even with indirect probing, it may be difficult to distinguish whether the node failed or an indirect probe message was lost due to network congestion or other network issues. SUMMARY

An object may be to improve a failure detection system of the above mentioned kind, while overcoming or at least alleviating the above mentioned disadvantage.

According to an aspect, the object is achieved by a method, performed by a first node, for selecting a second node for transmission of an indirect probe message for detection of failure of a third node. A network comprises the first, second and third nodes. The first node selects the second node based on information about topology of the network. The first node sends, to the second node, a request for instructing the second node to transmit the indirect probe message towards the third node.

According to another aspect, the object is achieved by a first node configured for selecting a second node for transmission of an indirect probe message for detection of failure of a third node. A network comprises the first, second and third nodes. The first node is configured for selecting the second node based on information about topology of the network. The first node is configured for sending, to the second node, a request for instructing the second node to transmit the indirect probe message towards the third node.

According to further aspects, the object is achieved by a computer program and a computer program carrier corresponding to the aspects above.

As an example, a direct probe message, e.g. transmitted by the first node towards the third node, may have failed. However, as described in the background section, the first node is not able to determine whether the failed direct probe message indicates a real fault, due to that the third node is faulty, or the failed direct probe message was caused by a possibly existing network issue.

Accordingly, thanks to that the first node selects the second node based on the information about topology of the network, it is intended to reduce a risk for that the possibly existing network issue also causes the indirect probe message to fail. In case the indirect probe message fails, i.e. even when the second node has been selected based on the information about topology, it may be concluded that the third node has failed.

An advantage is hence that a rate of false detections of faulty nodes may be reduced. Therefore, the embodiments herein may reduce number of false reports about faulty nodes, which are caused by network issues, such as congestion, severe delays and the like, rather than lack of response from the node that was reported as faulty.

BRIEF DESCRIPTION OF THE DRAWINGS

The various aspects of embodiments disclosed herein, including particular features and advantages thereof, will be readily understood from the following detailed description and the accompanying drawings, which are described briefly in the following.

Figure 1 is a combined signaling and flowchart illustrating a method according to prior art.

Figure 2 is a schematic overview of an exemplifying network in which

embodiments herein may be implemented.

Figure 3 is a combined signaling and flowchart illustrating the methods herein.

Figure 4 is a block diagram illustrating embodiments of the first node.

DETAILED DESCRIPTION

In order to better appreciated the embodiments herein, some observations and analysis of the prior art, as realized by the present inventors, is provided in the following.

It has been found that the SWIM solution, presented in the background section, may not, at least in some cases, reduce the number of false alarms. A reason for this may be that the nodes, which shall send the indirect probe message, are picked randomly. It may then happen that the picked node resides in the same network segment as the node that initially probed with a direct probe message. Therefore, the indirect probe message may be lost again. It may then erroneously be concluded that the node under observation is faulty even if it actually is alive.

Throughout the following description, similar reference numerals have been used to denote similar features, such as nodes, actions, modules, circuits, parts, items, elements, units or the like, when applicable. In the Figures, features that appear in some embodiments are indicated by dashed lines.

Figure 2 depicts an exemplifying network 100 in which embodiments herein may be implemented. In this example, the network 100 may be a cloud infrastructure. In other examples, the network 100 may be data center, a computer network, a cloud network, a cloud platform, a communication network or the like. The network 100 may be a portion, such as an underlying infrastructure, of any known communication system, such as any Third Generation Partnership Project (3GPP) network or the like,

The network 100 comprises a first node 110, a second node 120 and a third node 130. As used herein, the term“node” may refer to a physical, logical or virtual entity of the network 100. Physical entity may refer to a set of hardware resources, such as memory, processor, network interfaces and the like, which may be located within a single casing. Logical or virtual entity may refer to a container in a cloud platform, a virtual machine, an execution environment, an application, a service or the like. Virtual machine may be formed by a collection of hardware resource residing in different casings, racks, sleds, blades or the like, of a so called disaggregated hardware system.

Each node, such as the first and second nodes 1 10, 120, of the network 100, may manage a probe list. Each node is responsible for maintaining the probe list and for sending of direct probe message to the nodes of the probe list. In this manner, each node may handle its responsibility for detecting failure of other nodes, i.e. neighboring nodes in the network 100. The probe list indicates an order and/or a frequency of probing for each node in the probe list. The probe list may include identities of nodes to be probed, where e.g. nodes at the beginning of the probe list are probed first.

If there is no response to a direct probe message before a timeout expires, the node that transmitted the direct or indirect probe message may label the node, that was probed, as faulty or at least as suspected as faulty.

A neighbor list of said each node may indicate all nodes in the network 100 that are known as neighbors to said each node. Each node may probe the nodes given by the neighbor list periodically. Also nodes that may perform indirect probing are selected from the neighbor list.

It may here be said that the terms“probing”,“probe” herein refers to a transmission of a probe message, be it an indirect probe message or direct probe message.

Furthermore, one or more other components for management of the network 100 may also execute in at least some nodes of the network 100. The component(s) may handle resource scheduling, memory management or the like. The network 100 may further be said to comprise a managing node 140, which e.g. manages information about topology of the network 100. As an example, the managing node 140 may maintain network or physical information that may indicate topological relationships between the nodes 1 10, 120, 130 in the network 100, in particular those nodes that appear in the neighbor list. The information about topology may for example indicate a distance in terms of one or more of rack, sled, casing, blade, subnet, hops and the like.

Figure 3 illustrates an exemplifying method according to embodiments herein when implemented in the network 100 of Figure 2.

The first node 1 10 performs a method for selecting the second node 120 for transmission of an indirect probe message for detection of failure of the third node 130. As mentioned, the network 100 comprises the first, second and third nodes 1 10, 120, 130.

One or more of the following actions may be performed in any suitable order.

Action A010

The managing node 140 may send information about topology to the first node 1 10. The information about topology may be sent on request from the first node 1 10 and/or periodically according to a pre-defined or dynamically configurable pattern or frequency.

Action A020

Subsequent to action A010, the first node 1 10 may obtain the information about topology of the network 100.

This action may be realized in many different manners, such as exemplified by action A030, A040 or the like. This means that the obtaining of the information about topology may comprise one or more of action A030, A040 and the like.

Action A030

The first node 110 may receive the information about topology from a managing node 140 of the network 100. The managing node 140 may handle updating and distribution of the information about topology.

The managing node 140 may have access to a database (not shown) storing information about topology. The database’s information about topology may have been collected from the network 100, e.g. from the above mentioned other components.

Application-Layer Traffic Optimization (ALTO) Server Discovery to S. Kiesel, M.

Stiemerling, N. Schwan, M. Scharf, H. Song., published in November 2014, RFC7268, describes a function for this purpose.

Action A040

The first node 1 10 may determine a virtual network coordinate for the first node 1 10 based on latency to nodes of the network 100. Determination of a virtual network coordinate is known in the art, such as described“Vivaldi: a decentralized network coordinate system”, by Frank Dabek, Russ Cox, Frans Kaashoek, and Robert Morris, published in 2004, SIGCOMM Comput. Commun. Rev. 34, 4 (August 2004), 15-26. DOI: https://doi.Org/10.1 145/1030194.1015471 .

Action A050

In some embodiments, the first node 1 10 may send a direct probe message towards the third node 130. Action A060 and action A070 may then performed when no response to the direct probe message is received from the third node 130 within a time period indicating allowable response time for nodes in the network 100.

In these embodiments, action A060 and A070 may be performed to validate whether or not it may be correct to assume that the third node 130 is faulty, or if the lack of response from the third node 130 may have been caused by a possibly existing network issue.

Action A060

The first node 1 10 selects the second node 120 based on information about topology of the network 100.

The information about topology may comprise information about which node of the network 100 belongs to which subnet of the network 100. The second and third nodes 120, 130 may belong to one and the same subnet of the network 100. The information about topology may be describe a topology neighborhood, whereby the first node 1 10 is able to identify the second node 120 as the node among the neighbors to the third node 130 whose path towards the third node 130 is least, or among the least, likely to be exposed to the same network issue as a path between the first node 1 10 and the third node 130.

When the first node 110 selects a node, such as the second node 120, to perform indirect probing towards a suspected node, such as the third node 130, it may retrieve information from the managing node 140 as in action A030.

Then, the first node 1 10 may make a decision according to a set of pre-defined or dynamically configurable rules. For example, the first node 1 10 may select the second node 120 because it is in the same rack as the third node 130, because it is in the same subnet as the third node 130 or the like.

In more detail, the first node 1 10 may select the second node because a first network topological relationship between the second node 120 and the third node 130 is different from a second network topological relationship between the first node 110 and the third node 130. Here, the expression“network topological relationship” may refer to number of hops between two nodes, paths between two nodes or the like. When considering paths between nodes it may be enough that the paths are at least partially different in order to conclude that the first and second relationships are different. A more strict application of the path would require the entire paths to be different in order to conclude that the first and second relationships are different.

In this manner, it may be intended to at least reduce the risk of that one and the same network issue causes both the direct probe message and the indirect probe message to fail. Thereby, probability of a false detection, indicating that the third node is faulty, is reduced.

In some cases, the first node 1 10 may check the information about topology to find any nodes that reside in the same rack as the third node 130. If not, the first node 1 10 may continue by checking the information about topology to find any nodes in the same subnet as the third node 130. If not, the first node 1 10 may then select the node that is closest to the third node 130 in terms of network cost or network distance. The network cost e.g. between two nodes may refer to Round Trip Time (RTT) between the nodes, a number of hops between the nodes or the like.

In one further example, when the second node 120 and the third node 130 to be probed are“near” each other in terms of network topology, a risk of that a network congestion causes the probing to fail is reduced since the network path between the nodes is typically“shorter” than if the second node 120 is selected randomly.

In yet another example, it may be preferred to selected the second node 120 such that a path towards the third node is different (longer or shorter) from the path used when the direct probing failed.

Action A070

The first node 1 10 sends, to the second node 120, a request for instructing the second node 120 to transmit the indirect probe message towards the third node 130.

Action A080

The second node 120 may receive the request. Subsequently, the second node 120 may transmit a probe message towards the third node 130 as instructed by the request from the first node 1 10.

With reference to Figure 4, a schematic block diagram of embodiments of the first node 1 10 of Figure 2 is shown.

The first node 1 10 may comprise a processing unit 401 , such as a means for performing the methods described herein. The means may be embodied in the form of one or more hardware units and/or one or more software units. The term“unit” may thus refer to a circuit, a software block or the like according to various embodiments as described below.

The first node 1 10 may further comprise a memory 402. The memory may comprise, such as contain or store, instructions, e.g. in the form of a computer program 403, which may comprise computer readable code units.

According to some embodiments herein, the first node 1 10 and/or the processing unit 401 comprises a processing circuit 404 as an exemplifying hardware unit, which may comprise one or more processors. Accordingly, the processing unit 401 may be embodied in the form of, or‘realized by’, the processing circuit 404. The instructions may be executable by the processing circuit 404, whereby the first node 1 10 is operative to perform the methods of Figure 3. As another example, the instructions, when executed by the first node 1 10 and/or the processing circuit 404, may cause the first node 1 10 to perform the method according to Figure 3. In view of the above, in one example, there is provided a first node 1 10 for selecting a second node 120 for transmission of an indirect probe message for detection of failure of a third node 130. As mentioned, the network 100 comprises the first, second and third nodes 1 10, 120, 130. Again, the memory 402 contains the instructions executable by said processing circuit 404 whereby the first node 1 10 is operative for: selecting the second node 120 based on information about topology of the network 100, and

sending, to the second node 120, a request for instructing the second node 120 to transmit the indirect probe message towards the third node 130.

Figure 4 further illustrates a carrier 405, or program carrier, which comprises the computer program 403 as described directly above. The carrier 405 may be one of an electronic signal, an optical signal, a radio signal and a computer readable medium.

In some embodiments, the first node 1 10 and/or the processing unit 401 may comprise one or more of a selecting unit 410, a sending unit 420, an obtaining unit 430, a receiving unit 440, and a determining unit 450 as exemplifying hardware units. The term“unit” may refer to a circuit when the term“unit” refers to a hardware unit. In other examples, one or more of the aforementioned exemplifying hardware units may be implemented as one or more software units.

Moreover, the first node 1 10 and/or the processing unit 401 may comprise an Input/Output unit 406, which may be exemplified by the receiving unit and/or the sending unit when applicable.

Accordingly, the first node 110 is configured for selecting a second node 120 for transmission of an indirect probe message for detection of failure of a third node 130. A network 100 comprises the first, second and third nodes 1 10, 120, 130.

Therefore, according to the various embodiments described above, the first node 1 10 and/or the processing unit 401 and/or the selecting unit 410 is configured for selecting the second node 120 based on information about topology of the network 100. The first node 1 10 and/or the processing unit 401 and/or the sending unit 420 is configured for sending, to the second node 120, a request for instructing the second node 120 to transmit the indirect probe message towards the third node 130. The information about topology may comprise information about which node of the network 100 belongs to which subnet of the network 100. The second and third nodes 120, 130 may belong to one and the same subnet of the network 100.

The first node 1 10 and/or the processing unit 401 and/or the sending unit 420, or another sending unit (not shown), may be configured for sending a direct probe message towards the third node 130. The first node 1 10 and/or the processing unit 401 and/or the selecting unit 410 may be configured for selecting the second node 120 and the first node 1 10 and/or the processing unit 401 and/or the sending unit 420 may be configured for sending the request when no response to the direct probe message is received from the third node 130 within a time period indicating allowable response time for nodes in the network 100.

The first node 1 10 and/or the processing unit 401 and/or the obtaining unit 430 may be configured for obtaining the information about topology of the network 100.

The first node 1 10 and/or the processing unit 401 and/or the obtaining unit 430 is configured for obtaining the information about topology according to one or more different manners as described in the following.

The first node 1 10 and/or the processing unit 401 and/or the receiving unit 440 may be configured for receiving the information about topology from a managing node 140 of the network 100. The managing node 140 may handle updating and distribution of the information about topology.

Additionally or alternatively, the first node 1 10 and/or the processing unit 401 and/or the determining unit 450 may be configured for determining a virtual network coordinate for the first node 1 10 based on latency to nodes of the network 100.

As used herein, the term“node”, or“network node”, may refer to one or more physical entities, such as devices, apparatuses, computers, servers or the like. This may mean that embodiments herein may be implemented in one physical entity. Alternatively, the embodiments herein may be implemented in a plurality of physical entities, such as an arrangement comprising said one or more physical entities, i.e. the embodiments may be implemented in a distributed manner, such as on cloud system, which may comprise a set of server machines. In case of a cloud system, the term“node” may refer to a virtual machine, such as a container, virtual runtime environment or the like. The virtual machine may be assembled from hardware resources, such as memory, processing, network and storage resources, which may reside in different physical machines, e.g. in different computers.

As used herein, the term“unit” may refer to one or more functional units, each of which may be implemented as one or more hardware units and/or one or more software units and/or a combined software/hardware unit in a node. In some examples, the unit may represent a functional unit realized as software and/or hardware of the node.

As used herein, the term“computer program carrier”,“program carrier”, or “carrier”, may refer to one of an electronic signal, an optical signal, a radio signal, and a computer readable medium. In some examples, the computer program carrier may exclude transitory, propagating signals, such as the electronic, optical and/or radio signal. Thus, in these examples, the computer program carrier may be a non-transitory carrier, such as a non-transitory computer readable medium.

As used herein, the term“processing unit” may include one or more hardware units, one or more software units or a combination thereof. Any such unit, be it a hardware, software or a combined hardware-software unit, may be a determining means, estimating means, capturing means, associating means, comparing means, identification means, selecting means, receiving means, sending means or the like as disclosed herein. As an example, the expression“means” may be a unit corresponding to the units listed above in conjunction with the Figures.

As used herein, the term“software unit” may refer to a software application, a Dynamic Link Library (DLL), a software component, a software object, an object according to Component Object Model (COM), a software function, a software engine, an executable binary software file or the like.

The terms“processing unit” or“processing circuit” may herein encompass a processing unit, comprising e.g. one or more processors, an Application Specific integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or the like. The processing circuit or the like may comprise one or more processor kernels.

As used herein, the expression“configured to/for” may mean that a processing circuit is configured to, such as adapted to or operative to, by means of software configuration and/or hardware configuration, perform one or more of the actions described herein.

As used herein, the term“action” may refer to an action, a step, an operation, a response, a reaction, an activity or the like. It shall be noted that an action herein may be split into two or more sub-actions as applicable. Moreover, also as applicable, it shall be noted that two or more of the actions described herein may be merged into a single action.

As used herein, the term“memory” may refer to a hard disk, a magnetic storage medium, a portable computer diskette or disc, flash memory, random access memory (RAM) or the like. Furthermore, the term“memory” may refer to an internal register memory of a processor or the like.

As used herein, the term“computer readable medium” may be a Universal Serial Bus (USB) memory, a Digital Versatile Disc (DVD), a Blu-ray disc, a software unit that is received as a stream of data, a Flash memory, a hard drive, a memory card, such as a MemoryStick, a Multimedia Card (MMC), Secure Digital (SD) card, etc. One or more of the aforementioned examples of computer readable medium may be provided as one or more computer program products.

As used herein, the term“computer readable code units” may be text of a computer program, parts of or an entire binary file representing a computer program in a compiled format or anything there between.

As used herein, the expression“transmit” and“send” are considered to be interchangeable. These expressions include transmission by broadcasting, uni-casting, group-casting and the like. In this context, a transmission by broadcasting may be received and decoded by any authorized device within range. In case of uni-casting, one specifically addressed device may receive and decode the transmission. In case of group-casting, a group of specifically addressed devices may receive and decode the transmission.

As used herein, the terms“number” and/or“value” may be any kind of digit, such as binary, real, imaginary or rational number or the like. Moreover,“number” and/or “value” may be one or more characters, such as a letter or a string of letters.“Number” and/or“value” may also be represented by a string of bits, i.e. zeros and/or ones.

As used herein, the terms“first”,“second”,“third” etc. may have been used merely to distinguish features, apparatuses, elements, units, or the like from one another unless otherwise evident from the context.

As used herein, the term“subsequent action” may refer to that one action is performed after a preceding action, while additional actions may or may not be performed before said one action, but after the preceding action.

As used herein, the term“set of’ may refer to one or more of something. E.g. a set of devices may refer to one or more devices, a set of parameters may refer to one or more parameters or the like according to the embodiments herein.

As used herein, the expression“in some embodiments” has been used to indicate that the features of the embodiment described may be combined with any other embodiment disclosed herein.

Even though embodiments of the various aspects have been described, many different alterations, modifications and the like thereof will become apparent for those skilled in the art. The described embodiments are therefore not intended to limit the scope of the present disclosure.

Claims

1. A method, performed by a first node (1 10), for selecting a second node (120) for transmission of an indirect probe message for detection of failure of a third node (130), wherein a network (100) comprises the first, second and third nodes (1 10, 120, 130), wherein the method comprises:

selecting (A060) the second node (120) based on information about topology of the network (100), and

sending (A070), to the second node (120), a request for instructing the second node (120) to transmit the indirect probe message towards the third node (130).

2. The method according to claim 1 , wherein the information about topology comprises information about which node of the network (100) belongs to which subnet of the network (100), wherein the second and third nodes (120, 130) belong to one and the same subnet of the network (100).

3. The method according to claim 1 or 2, wherein the method comprises:

sending (A050) a direct probe message towards the third node (130), wherein the selecting (A060) of the second node (120) and the sending (A070) of the request are performed when no response to the direct probe message is received from the third node (130) within a time period indicating allowable response time for nodes in the network (100).

4. The method according to any one of the preceding claims, wherein the method

comprises:

obtaining (A020) the information about topology of the network (100).

5. The method according to the preceding claim, wherein the obtaining (A020) of the information about topology comprises one or more of:

receiving (A030) the information about topology from a managing node (140) of the network (100), wherein the managing node (140) handles updating and distribution of the information about topology, and

determining (A040) a virtual network coordinate for the first node (1 10) based on latency to nodes of the network (100).

6. A first node (1 10) configured for selecting a second node (120) for transmission of an indirect probe message for detection of failure of a third node (130), wherein a network (100) comprises the first, second and third nodes (1 10, 120, 130), wherein the first node (1 10) is configured for:

selecting the second node (120) based on information about topology of the network (100), and

sending, to the second node (120), a request for instructing the second node (120) to transmit the indirect probe message towards the third node (130).

7. The first node (1 10) according to claim 6, wherein the information about topology comprises information about which node of the network (100) belongs to which subnet of the network (100), wherein the second and third nodes (120, 130) belong to one and the same subnet of the network (100).

8. The first node (1 10) according to claim 6 or 7, wherein the first node (1 10) is

configured for:

sending a direct probe message towards the third node (130), wherein the first node (1 10) is configured for selecting the second node (120) and for sending the request when no response to the direct probe message is received from the third node (130) within a time period indicating allowable response time for nodes in the network (100).

9. The first node (1 10) according to any one of claims 6-8, wherein the first node (1 10) is configured for:

obtaining the information about topology of the network (100).

10. The first node (1 10) according to the preceding claim, wherein the first node (1 10) is configured for obtaining the information about topology by one or more of:

receiving the information about topology from a managing node (140) of the network (100), wherein the managing node (140) handles updating and distribution of the information about topology, and

determining a virtual network coordinate for the first node (1 10) based on latency to nodes of the network (100).

1 1 . A computer program (403), comprising computer readable code units which when executed on a first node (1 10) cause the first node (110) to perform a method according to any one of claims 1 -5.

12. A carrier (405) providing a computer program (403) according to the preceding claim, wherein the carrier (405) is one of an electronic signal, an optical signal, a radio signal and a computer readable medium.