Implementation and performance analysis of advanced IT services based on open source JAIN SLEE

Size: px
Start display at page:

Download "Implementation and performance analysis of advanced IT services based on open source JAIN SLEE"

Transcription

1 4th IEEE Workshop on Wireless and Internet Services WISe 2011, Bonn Implementation and performance analysis of advanced IT services based on open source JAIN SLEE M. Femminella, R. Francescangeli, E. Maccherani, L. Monacelli Dipartimento di Ingegneria Informatica ed Elettronica - DIEI Università degli Studi di Perugia Perugia, Italy {femminella, francescangeli, maccherani, monacelli}@diei.unipg.it Abstract The standard framework proposed by the JAIN SLEE specifications is emerging as a viable alternative for the development of advanced telecom services. The Mobicents JSLEE platform is the only open source implementation of those specifications. Its tuning is not trivial since it relies on several Java technologies implemented in multiple abstract layers. In this paper, we present the implementation of two realistic benchmark services and the relevant test campaign for the performance analysis of the Mobicents JAIN SLEE platform, with the aim of optimizing the achievable system throughput, for using it in a carrier-grade environment. Index terms - JAIN SLEE; SIP; Java; Transactions; MGCP; scalability analysis I. INTRODUCTION A Service Logic Execution Environment (SLEE) is a hosting environment for telecom applications, referred to as a container in Java terminology. The SLEE has been specifically designed to fulfill the requirements of telecom services, which are typically asynchronous and impose QoS network constraints [1], implement both stateful and stateless network control [2][3]. Being composed of several layers of abstraction, which are combined in a multi-tier architecture, a SLEE simplifies the development of new value-added services by providing the non-functional features needed for their execution. The resulting benefit is that the developer can focus only on aspects related to the implementation of the service logic, since the complexity of the underlying layers is masked by high-level APIs. The Java Community, within the Java APIs for Integrated Networks (JAIN) activities, offers a set of standard frameworks and open protocol APIs for the creation of telecommunications services. Telecom providers may greatly benefit from these technologies, as the utilization of standard common interfaces simplifies the integration of new services, and improves the interoperability with multiple networks, protocols and different end-user platforms [4]. Among those activities, the JAIN SLEE (JSLEE) activity provides a set of standardized specifications [5] for the implementation of a SLEE container. This kind of service hosting server is one of the most promising candidates for the deployment of application services in the new convergent telecommunications paradigm based on the IP Multimedia Subsystem (IMS) [25]. This paper focuses on the analysis of the performance of the Mobicents SLEE [6] (MSLEE), a JSLEE open source implementation, which operates on top of the JBoss Application Server (AS) [7]. To evaluate the platform performance, we have set up a test bed and created two realistic VoIP services, based on the Session Initiation Protocol (SIP) and the Media Gateway Control Protocol (MGCP) signaling protocols, which also include a high number of database queries. In fact, to the best of our knowledge, the performance tests of this very promising open-source platform have only been carried out with a test service named Mobicents load test [12], by far too simple when compared to actual, advanced telecom services. Our test bed was based on real-world operation conditions, in order to investigate about the platform suitability for the integration in a production environment. The choice of a test service based on SIP signaling is due to the widespread use of this signaling protocol. In fact, SIP is not only the de-facto standard for the signaling in VoIP and multimedia communications, but it has been also adopted by the IMS framework as the standard signaling protocol for user sessions (also in charge to transport other signaling protocols [20]), and recently it is also being used in other signaling scenarios (e.g. online gaming). In more details, in this paper we will: show relevant results about the impact of some configuration alternatives over the system performance. In particular, we will analyze the usage of transactions as well as the role of some key set up parameters of the Java-based framework; illustrate the system behavior under traffic load with Poisson and deterministic distributed arrivals; present critical aspects regarding some key platform mechanisms, especially focusing on the JBoss Transaction Manager. The MSLEE platform has been chosen since, at the time of writing, it is the only open source implementation compliant with the JSLEE v1.1 specifications. We already have verified that this platform is suitable for carrier-grade deployment, being a viable alternative to high-cost commercial SLEE solutions (see also our previous work [8]). This paper is organized as follows. The next section provides an overview of the platform architecture. Section III describes the performance benchmark testbed and methodology. Section IV presents the relevant results. Section /11/$ IEEE 746

2 V gives some final remarks. II. BGROUND A. JAIN SLEE The JSLEE activity specifies a Java-based, protocol-agnostic, event-oriented container for the execution of carrier grade telecom services [5]. Carrier grade advanced features cover data, user, and management planes, provide well assessed reliability and innovative features for any new type of service, such as dynamic brokering [9] and quality related pricing control, based on the actual consumed networking resources [10][11]. Various Java Enterprise Edition (JEE) technologies are employed in this framework, by adapting them to the specific needs of telecom applications. The service application logic is implemented in system components called Service Building Blocks (SBB). In operation, the JSLEE server creates a pool of SBB objects and manages them according to a well-defined lifecycle. SBBs operate asynchronously by receiving, processing, and triggering events. They can be attached to data streams called Activity Contexts, by which they receive events from other system entities. Also, SBBs may be linked together using parent-child relations, in order to implement the service logic in a modular fashion. In a JSLEE, events are internally managed by a functional element called Event Router, which delivers each event to the appropriate SBB. For what concerns the overall performance, this component plays a critical role, since it processes all system events. External network occurrences, such as SIP or other signaling protocol messages, are translated into internal Java events by so-called Resource Adaptors (RA). More generally, the set of implemented RAs constitutes an abstract interface layer that allows the SLEE to access external resources and interact with them. In practice, a developer who wants to enable service interoperability with a particular protocol stack can simply utilize the relevant RA interface methods in his service code (e.g. methods to access a particular SIP header field). Subsequently, the developer only needs to deploy the proper RA.jar file into the SLEE. B. Mobicents JAIN SLEE Server The Mobicents Communication Platform is an open source project, currently owned by Red Hat [6][13]. It includes a SLEE, a Media Server, a Presence Server, and a SIP Servlet Server. The counterparties are represented by Rhino, a commercial JSLEE by Open Cloud [22] and the Convergent Service Platform, a commercial JSLEE by Amdocs [23]. At the time of writing, the MSLEE is actively under development. In our performance tests, we have used the MSLEE version GA. This version comes with a SIP RA which is already compliant with the new JSLEE v.1.1 specifications. The MSLEE employs several JEE components, such as: Container Managed Persistence (CMP) fields, which enable data persistence for SBB objects; Java Database Connector (JDBC) drivers; Java Management Extensions (JMX) for the environment management and monitoring; Java Naming and Directory Interface (JNDI), which offers lookup functions for service registration. C. JBoss Application Server The MSLEE, as well as the other core servers of the Mobicents Platform, is installed on top of the JBoss AS [7]. JBoss acts as a hosting environment, that is to say, a container for containers. It offers capabilities such as service and SLEE configuration management, deployment, and thread pooling. D. System Configuration: Critical Aspects The resulting service platform is characterized by a considerable complexity, as it integrates the MSLEE framework, the JBoss AS, and the Java Virtual Machine (JVM). In order to achieve an efficient setup of the overall platform, some critical aspects of the architecture must be taken into account. 1) Java Memory Management Being based on the Java technology, the MSLEE relies on the automatic Java Garbage Collector (GC) mechanism for memory cleaning and defragmentation [14]. The drawback is that the developer does not have full control over the GC behavior, which may eventually lead to pauses in running applications [15]. Such pauses are clearly critical for telecom applications. As a matter of fact, the SLEE may freeze when dealing with post-pause avalanche restarts (during each pause, unprocessed messages accumulate in the event router queue). The JVM v.6 includes different GCs, in order to meet the requirements of different classes of applications [15]. In this paper, we present performance evaluated with the Parallel GC scheme only, which is the default one of the JVM. 2) Transactions In data critical environments, transactions are typically used in order to maintain a computer framework (i.e. a database, a file system or an application) in a known, consistent state, after system or database failures. As regards transactions, the MSLEE relies on the JBoss AS transaction system, which natively supports Java Transaction API (JTA), allowing any transaction manager implementation to be used. JBoss is by default configured to use the so-called JTA compatible in-vm transaction manager. It is very fast, but does have two limitations: it is incapable of automated recovery after a server crash; while it does support propagating transaction contexts with remote calls (Java Remote Method Invocation), it does not support the propagation of transaction contexts to other JVMs, so all transactional work must be done in the same JVM as the JBoss server. In some advanced telecom services, such as online banking transactions, the provider may need a transactional behavior to ensure that all operations made on the remote database (which may involve the transmission of subscriber personal information) remain consistent during all the system operation, 747

3 as well as after a system failure. Such a guarantee comes with a great performance overhead, in the form of disk writing operations, which are directly related to the number of transactions processed by the service. Therefore, is of great importance for the provider to carefully evaluate whether to use transactions or not, in order to ensure maximum performance. In practice, the service developer can: choose to use a JTA compatible Transaction Manager capable of automatic detection of those operations that do not need a transaction (i.e. read only SELECT database queries), in order to avoid unnecessary disk writing when the shared resource is accessed; manually configure the shared resource to be accessed either in a transactional or non-transactional way, by using two different connection pools. In this way, the developer is free to choose the transaction management when needed by his service. This is accomplished by simply inserting the JNDI reference to a proper transactional database connector in the code. Also, there can be VoIP services in which transactions are not needed at all, typically when performance requirements are most stringent. This is the case for forwarding, redirect and control VoIP services, for which there is no need to change the state of shared resources. III. BENCHMARK DESCRIPTION The Mobicents community has published a set of performance results [13], obtained by an automatic answering service in which the MSLEE operates like a simple SIP User Agent Server (UAS). This service, called Mobicents load test, is included as a service example in the MSLEE package. It is made of only one SBB which responds to the incoming call, completes the SIP three way handshake, and, after a pre-defined timer expires, sends a BYE request towards the caller SIP User Agent Client (UAC). Since the included load test is too simple to give an idea of the performance of an actual carrier-grade VoIP service, we have implemented two typical VoIP services in order to properly characterize the MSLEE performance in a realistic scenario. Our reference scenario is the trusted IP network of a telecom provider which offers VoIP SIP-based services by means of a MSLEE. The MSLEE is in charge of managing the entire signaling flow, by implementing a call control service. In more details, the service implements a SIP Back-to-Back User Agent (B2BUA) signaling architecture [16], which easily allows the introduction of a third party call control mechanism, very useful when it is necessary to introduce an additional entity controlling the access to a given resource (e.g. the subscriber credit stored in a remote database). In the following, we will present our two VoIP services and the test bed used for our measurement campaign. A. CallControl Service (CCS) This service implements a SIP B2BUA, in which the MSLEE acts both as UAS and UAC, by splitting each call in two SIP dialogs over two distinct call-legs (caller-slee and SLEE-callee, see Fig. 1). In this way, the service has complete control over the ongoing call, as it manages the entire signaling flow. We will refer to this service as CallControl Service (CCS). CCS includes two different timers: the first timer (Call Duration Timer CDT) is used to control the maximum call duration; the second timer (Periodic Database Query Timer PDQT) is used to perform periodic queries to the subscriber profile database. As regards the service operation, as illustrated in Fig. 1, when the initial is received, a root SBB queries the database to retrieve the subscriber profile, including the values of CDT and PQDT timers. Upon receiving the answer to the DB query, the SBB starts the CDT timer, and activates a child SBB called CallControl. The child SBB, in turn, creates the second call leg towards the callee, by initiating a new SIP session, and establishes the RTP media session between the two end points. During the call, the service keeps on querying the database every time the PQDT timer expires. The call comes to an end when the CDT expires making the CallControl SBB send a BYE request on both call legs, which is the case illustrated in Fig. 1. Alternatively, each of the two end points can normally send a BYE message, as shown in Fig. 2, to the other to close the call, prior to the CDT expiration. In this case the MSLEE server simply forwards the BYE message to the other end point and the call is terminated. In both cases, upon call termination by the user or by the CDT, the service performs an additional, final database query. Call duration Figure 1. CCS signaling flow, termination upon CDT expiration. This service could represent an online charging system for pre-paid VoIP calls, which periodically updates the user credit in the subscriber profile by accessing a remote database (see also [21]). However, given the widespread usage of the SIP protocol in several different scenarios, it could simulate a lot of 748

4 other services, also beyond the IP telephony world. In addition, being the MSLEE compliant with JSLEE specifications v1.1, it is also suitable for a variety of application domains demanding event driven architecture for high volume and low latency signaling, even if originally conceived as a VoIP platform. Call duration Figure 2. CCS signaling flow, termination by user. B. CallControl with Media Announcement Service (CCMAS) The second service we implemented is more VoIP oriented than the first one, and it also showcases the protocol-agnostic capabilities of the JSLEE container. This service, called CallControl with Media Announcement Service (CCMAS) makes use of two different network signaling entities: the MSLEE and the Mobicents Media Server (MMS). The MMS is implementable by using an MSLEE with multimedia streams handling functions and supporting various media server endpoints like: announcement, Interactive Voice Response (IVR), packet relay, conference, and loop. All these capabilities are controlled by a local Media Server Controller (MSC) API which can be used within a normal MSLEE SBB. In order to realize the CCMAS, we have implemented a MSC [26] which, by taking advantage of the deployed MGCP RA, decodes MGCP messages and, after some processing, converts them in local MSC API calls. Also, our MSC component can be controlled remotely and it can be deployed in any network architecture that utilizes the MGCP protocol for media gateway control. In this service scenario, the CCMAS establishes and controls a communication between a UAC and a UAS by using the same B2BUA architecture of the CCS described in section III.A. In CCMAS, the B2BUA exploits the additional MGCP support in order to provide audio announcements during the call to the caller (see Fig. 3). These audio announcements are typically used in carrier-grade VoIP services as remaining credit reminders and as call termination messages. As in CCS, this service makes use of two timers also called CDT and PQDT having the same behavior of the CCS ones. For what concerns the signaling flow, when the initial is received, a root SBB queries the database to retrieve the subscriber profile, including the values of CDT and PQDT timers. Upon receiving the answer to the DB query, the SBB starts the CDT timer, and activates the CallControlMAS child SBB. The child SBB completes the SIP session setup as illustrated in Fig. 3. While the call is active, upon reaching a pre-configured threshold (for example a remaining level of credit in the subscriber profile), the CallControlMAS SBB redirects the UAC session to the MMS using a SIP re-. The re- session handshake triggers an MGCP message exchange that results in the creation of a new RTP session between the UAC and the MMS for the audio announcement (Fig. 3). In particular, an MGCP Create Connection command (CRCX) is sent to the MMS. The CRCX contains the Session Description Protocol (SDP) parameters that are included in the re- message and the particular MMS Endpoint to be used (Announcement, in our case). The MMS processes the CRCX command, creates the Endpoint according to the SDP, and responds to the MSLEE with a (Transaction Executed) message that contains the Endpoint SDP and a Connection Identifier, in order to properly setup the media streaming flow. At this point, the MSLEE proceeds with the 3-way handshake with the client and, when the SIP session is established, a Notification Request command (RQNT) is sent to the MMS in order to start the audio streaming. With the RQNT the service specifies the URL of the particular audio file to be played and the request to notify the MSLEE when the announcement is completed. The MMS answers the RQNT and starts to play the announcement message, by sending RTP packets directly to the client. Once completed, the MMS sends a Notify (NTFY) command to the MSLEE to indicate that the RTP flow has ended. The MSLEE replies with a response and sends a Delete Connection (DLCX) command to release the resources used by the endpoint-connection link. Upon the audio stream termination, another SIP re- handshake is used to restore the original UAC-UAS session. During the audio announcement the CDT and PDQT timers are paused until the end of the audio message. As already pointed out for CCS in section III.A, the call comes to an end either when the CDT expires or when one of the two clients sends a BYE message. In the former, as soon as the timer expires, another re- connects the UAC to the MMS that plays another audio stream used to inform the user about the end of the credit while the UAS is disconnected with a BYE message. C. Testbed Topology and Configuration As regards the transport protocol, we have adopted UDP, since it is the common choice in most SIP configurations. We plan to investigate the usage of TCP in a server-server (between MSLEE and MMS) scenario as future work. The testbed topology used in our test campaign is depicted in Fig. 4. The MSLEE and MMS, based on Mobicents v GA and deployed on JBoss v GA, have been installed on Fujitsu-Siemens server-class machines PRIMERGY TX300 S4 with dual Intel Xeon 2.33 GHz (i.e. 8 CPU cores) and 16GB RAM. Servers OS were Arch Linux x64 (kernel ). 749

5 UAC 180 Ringing OK OK OK OK BYE OK SLEE UAS UAC RTP Stream CDT/PQDT start Signal threshold End of Credits 180 Ringing OK CREATE CX REQ NOTIFY RTP Stream NOTIFY DELETE CX BYE OK CREATE CX REQ NOTIFY RTP Stream NOTIFY DELETE CX Callee UAS Policy Selector query Billing database query request Billing database query request Billing database query request Billing database query request Media Server Figure 3. CCMAS signaling flow (SIP messages in black arrows, MGCP messages in red arrows). Database The MySQL connector can be manually configured to use or not transactions. This is achieved by properly configuring the datasource mysql-ds.xml file contained in the JBoss deploy folder. Moreover, we have used the prepared statement cache option for data sources in order to improve the execution of frequent MySQL queries [19]. In order to configure the JVM heap (setting the equal max and min values as recommended in [19]) and select the Parallel GC we have added the following command line flags to the configuration script of the JBoss AS, in this case setting a 6GB heap: -Xms6000m -Xmx6000m -XX:+UseTLAB We have used the Mobicents JAIN SIP RA v and we have tuned it by increasing the number of concurrent threads, in order to allow a greater number of events to be processed at once. As regards the MGCP RA, version GA has been used. We also have run the JAIN SLEE 1.1 Technology Compatibility Kit (TCK) on the MSLEE server, which have successfully passed all tests. All logs have been disabled during the execution of the tests to improve MSLEE and JBOSS AS performance. As for the traffic statistics, the SIPp UAC has been set to generate new SIP calls with both a deterministic and a Poisson arrival rate distribution with an average rate equal to. Every test has been carried out by using a constant value for 60 minutes. The value for the CDT timer has been set to 3 minutes, which represents also the maximum call duration. By default, the UAC SIPp scenario has been configured to let the MSLEE to close the call on CDT expiration. The default value for the PQDT timer has been set equal to. Before collecting statistics, we have performed a warm up sessions of 15 minutes to allow the Java GC to be executed at least once and avoid both JVM and MSLEE transient effects. Figure 4. Testbed configuration. The JVM was the v.1.6.0_11 64-bit Server. In addition, we have used the following software tools: the SIPp traffic generator [18] to simulate the UAC and the UAS end points, installed on two Linux-based PCs with Ubuntu v.8.0.4; the MySQL database server v a, and the MySQL Connector/J v JDBC for the database access, deployed on a remote Linux box. Each database interrogation relied on an object-relational mapping by using an Enterprise Java Bean 3.0 object, which is implemented through the Hibernate technology. This function is provided by the JBoss application server. IV. NUMERICAL RESULTS In the following, we present the performance results obtained for the CCS and CCMAS services evaluated with the test bed shown in Fig. 4. We have considered a number of possible conditions which are likely to occur in production environments. In more detail, in section IV.A, we have tested the impact of the frequency of queries during a call, and the influence of the amount of Java heap allocated to the JVM. In section IV.B, we evaluated how the MSLEE behaves when a non-deterministic pattern of arrivals is present. In section IV.C, we have analyzed the impact of the usage of transactions associated to database queries, which is an option that can be required by specific services. Finally, in section IV.D, we have investigated the performance of the MSLEE when dealing with multiple underlying signaling protocols measuring the throughput of the CCMAS, described in section III.B. In all tests the metric used to assess performance is the maximum call throughput, defined as the maximum load ensuring at least a 95% of successful calls. A. Server Scalability and JVM Tuning In order to verify the SLEE scalability, we have tested the 750

6 system with the CCS, by setting the PQDT to 3, 10 and 30 seconds. For each run considered in this subsection, the traffic arrival pattern was deterministic. The call duration, equal to 3 minutes, has been set by configuring the UAC SIPp scenario to let the MSLEE to close the call upon CDT expiration. In this test the MySQL connector has been configured with DB transactions enabled. Fig. 5 depicts the throughput achieved versus offered load, both expressed in calls per second (cps). Five curves are showed. The curve with the black-square bullets represents the theoretical throughput when no calls are lost. Let us focus on the curves with Java heap equal to 6 GB. The trend shown in the figure confirms our expectations: the higher the frequency of database queries, the higher the number of events processed by the Event Router, thus the lower the throughput. In addition, since we use database transactions, this implies also the presence of a process which writes data on the hard disk for each query. To sum up, the maximum throughput achievable by the MSLEE is scalable with the complexity of the deployed service. Also, we have compared the system performance with two different values of the JVM heap (7 GB and 6 GB), having the PQDT set equal to. Fig. 3 points out how the MSLEE performance increases with a larger amount of allocated memory. In more detail, increasing the Java heap from 6 GB to 7 GB, the maximum throughput goes from 6 cps to 15, thus the service is really sensible to the amount of memory allocated to JVM. In all following sections, measurement tests have been run using the 7 GB heap setup with the PDQT set to 10s. B. Poisson vs. Deterministic Arrivals We have compared the system throughput performance as a function of offered traffic load with deterministic and Poisson distributed arrivals. This choice is motivated by the fact that the Poisson process is a good model for real arrival patterns, especially of VoIP calls, as shown in the work [17]. SIPp generates each SIP call by parsing an external script file called scenario, which may include actions like sending and receiving a SIP message, as well as pauses. By default, SIPp only offers constant rate call generation, set by the proper command line option, eventually further spaced in time by pauses characterized by some common probability distribution, but does not include the Poisson arrival process. To overcome this limitation, we have created a custom scenario applying the following strategy. A Poisson arrival process implies a set of exponentially distributed interarrival times, with average rate. In a given time interval [0, T] where T>>1/, it is known that a Poisson arrival process distributes any given set of arrivals uniformly over T. Thus, in order to produce a Poisson process with rate, we have to generate a number of T arrivals, each of them with a uniform distributed probability to occur in a time instant x ranging in [0, T]. In practice, we have generated all the T calls in a very short time interval [0, t] at the beginning of the test, where t<<t (t is set to ), and delayed the sending of the message by inserting a random pause, uniformly distributed in [0, T-t], so as to have all arrivals in [t, T]. This approach follows the description provided in section 2.5 of [27]. We have verified, through an extensive analysis of traffic traces, that the obtained arrival process actually approximates very closely the Poisson distribution. Fig. 6 reports, on the abscissa, the interarrival times (in seconds) and, on the ordinate, the estimated pdf (on a logarithmic scale). Clearly, a straight line represents a pure Poisson process. Our approximation is valid up to 10-5 which is reasonable since we used 1,500,000 samples. Both interarrival times average, equal to s, and the standard deviation, equal to s, are very close to the theoretical value of 0.04s, corresponding to =25 cps. In this specific test, for calls with Poisson arrivals, we adopted both deterministic and exponentially distributed call durations. In case of exponentially distributed call duration, the average value has been set equal to 180 seconds. This means that about 37% of the calls are closed by the MSLEE and last for 3 minutes, while the remaining calls are shorter and closed by the UAC. The resulting average call duration, due to the effect of tail truncation by the MSLEE, is equal to s. Fig. 7 shows the throughput (in cps) versus the arrival rate (cps) of the CCS. One curve is the classic theoretical one, which indicates the ideal behavior without losses. The one with the plus-shaped bullets is the same curve already seen in Fig. 6. The other two curves represent a test with Poisson arrivals and call length fixed to 3 minutes (star bullets), and Poisson arrivals and call length exponentially distributed (cross bullets). As expected, since a Poisson distribution of the arrival process offers a bursty traffic pattern, a performance drop takes place with respect to the all deterministic scenario. A further comment is necessary to explain the behavior of the Poisson arrivals with exponential call duration curve. In fact, since using an exponential distribution for the call duration leads to a shorter value of average call length, given a value of the abscissa (in cps) the resulting offered load (measured in erlang = cps x call duration) for the relevant curve is lower than the one of the other curves as shown in Fig. 8. Throughput (cps) HEAP = 7 GB, Timer 10s HEAP = 6 GB, Timer 3s 2 HEAP = 6 GB, Timer 10s HEAP = 6 GB, Timer 30s Theoretical - No losses Arrival rate (cps) Figure 5. CCS Scalability benchmark. 751

7 Estimated PDF throughput when transactions are disabled. The PQDT is still set to 10s, the Java heap to 7 GB, and the traffic statistic is completely deterministic in arrival rate and call length. As expected, the related disk writing operations have a major impact on the system performance and represent a real system bottleneck, even if high speed disks are being used in the testbed (Serial Attached SCSI at 15,000 rpm). The maximum throughput rises from 15 cps to 60 cps when transaction are disabled. Throughput (cps) 1e-05 1e-06 1e Interarrival times (seconds) Figure 6. Assessment of Poisson properties for call arrivals Det. arrivals, Det. duration Poisson arrivals, Exp. duration Poisson arrivals, Det. duration Theoretical - No losses Arrival rate (cps) Figure 7. CCS Poisson vs. Deterministic arrival process (cps). This is a first explanation for the apparent better behavior of the Poisson curve. In addition, having an average shorter call length means less database queries (fewer PQDT expirations) and also to avoid the CDT expiration and processing, thus a lower load for the MSLEE Event Router and for the DB connector, which in this test uses transactions. In any case, when curves are plotted in erlang, as in Fig. 8, so as to neglect the impact of call duration, the best performing configuration is again the deterministic one. To sum up, the performance loss due to bursty arrivals is not so severe, and thus the MSLEE seems to be robust also with respect to more bursty, realistic arrival patterns. A further observation is that the presence of bursts in Poisson patterns causes a sudden system crash, as it enters the overload condition. C. System Performance: Utilization of Transactions In this test, we have evaluated the impact of transactions and the consequent disk writing operations. In Fig. 9, shows three curves: the usual ideal curve corresponding to the no loss condition; the throughput when transactions are enabled; the D. CCMAS System Performance In this subsection we present preliminary results about system performance, calculated as call throughput, of the MSLEE when running the CCMAS service. As in section IV.C, the PQDT is set to 10s, the Java heap is set to 7 GB, and the traffic statistic is deterministic in arrival rate and call length (3 minutes). Given the service type, the JTA transaction system has been disabled. Under these conditions, the maximum call throughput reached with CCMAS has been 24cps. This result is perfectly reasonable since, as illustrated in Fig. 9, the same service without the audio announcements (CCS), under the same test conditions, reached a maximum throughput of 60 cps. The reason of the performance drop can be found in the higher number of SIP transactions processed. In fact, in CCS there are only 4 SIP transactions (2 s, 2 BYEs) whereas in CCMAS there are 7 SIP transactions, nearly the double. Also, the additional SIP transactions are of the re- type, which require a lot of internal processing. In addition to the increase in SIP transactions, there is also the MGCP exchanges management to take into account that weigh on the MSLEE. V. CONCLUSION This paper illustrates how advanced networked services can be effectively provisioned in a converged telecommunications architecture by using a completely open source solution, implementing the JSLEE specifications, the Mobicents Communication Platform. This solution is able to work as a carrier-grade service container within different service frameworks (SOA, IMS, or custom ones). Its capabilities of managing sessions have been illustrated through the implementation of two real-world services, CCS and CCMAS, able to handle signaling for advanced, multimedia scenarios. Moreover, we have provided an overview of critical issues in the deployment and in the operation phases of the MSLEE, by describing some configuration options along with the relevant criticalities. The performance test campaign also resulted in useful indications so as to improve performance, defined as the maximum call throughput, of the MSLEE server under real-world operating conditions. Finally, the security vs. performance compromise has also been investigated through the analysis of the impact of the database transactions on the system performance. To further improve performance, more virtual instances of the MSLEE server can be run in parallel within the same physical machine. This is of actual interest for service operators, since it is a further motivation to consolidate servers and it is thoroughly examined in [24]. 752

8 Throughput (erl) Throughput (cps) Det. arrivals, Det. CHT 500 Poisson arrivals, Exp. CHT Poisson arrivals, Det. CHT Theoretical - No losses Offered load (erl) Figure 8. CCS Poisson vs. Deterministic arrival process (erl) Transactions on, timer Transactions off, timer Theoretical - No losses Arrival rate (cps) Figure 9. Transaction impact on CCS throughput. REFERENCES [1] C. Casetti, M. Gerla, S.S.Lee, G. Reali, Resource Allocation and Admission Control Styles in QoS DiffServ Networks, International Workshop on QoS in Multiservice IP Networks (QoS-IP 1), Rome, Italy January, 1. [2] N. Blefari-Melazzi, M. Femminella, "Stateful vs. Stateless Admission Control: which can be the gap in utilization efficiency?," IEEE GLOBECOM 2, November, 2, Taipei, Taiwan. [3] N. Blefari-Melazzi, JN Daigle, N Femminella,"Stateless admission control for QoS provisioning for VoIP in a DiffServ domain", 18th International Teletraffic Congress (ITC 18), 31 August - 5 September, 3, Berlin, Germany. [4] R. M. Perea, Internet Multimedia Communications Using SIP, Morgan Kaufmann, 8. [5] JSR 240, JAIN SLEE v1.1 Web Site [6] Mobicents Web Site, available at: [7] JBoss Web Site, available at: [8] M. Femminella, R. Francescangeli, F. Giacinti, E. Maccherani, A. Parisi, G. Reali, Design, Implementation, and Performance Evaluation of an Advanced SIP-based Call Control for VoIP Services, IEEE ICC 9, Dresden, Germany. [9] D. Di Sorte, G. Reali, Pricing and brokering services over interconnected IP networks, Journal of Network and Computer Applications, 28 (5) [10] N. Blefari-Melazzi, D. Di Sorte, G. Reali: Usage-based Pricing Law to Charge IP Network Services with Performance Guarantees, IEEE International Conference on Communications (ICC) 2, New York, USA, 2 [11] Di Sorte, M. Femminella, G. Reali, A QoS Index for IP Services to Effectively Support Usage-based Charging IEEE Communications Letters, Vol. 8, No. 11, November 4. [12] M. Femminella, R. Francescangeli, F. Giacinti, E. Maccherani, A. Parisi, G. Reali, Scalability and Performance Evaluation of a JAIN SLEEbased Platform for VoIP Services, 21st International Teletraffic Congress (ITC 21), Paris, September 9. [13] Mobicents Google Pages Web Site, available at: http :// groups.google.com/group/mobicents-public/web?pli=1. [14] Java SE 6 HotSpot Virtual Machine GC Tuning, Web Site: ailable_collectors. [15] Bruno Van Den Bossche et al., J2EE-based Middleware for Low Latency Service Enabling Platforms, proceedings of Global Telecommunications Conference, 6. [16] J. Rosenberg et al., SIP: Session Initiation Protocol, IETF RFC [17] R. Birke, M. Mellia, M. Petracca, Understanding VoIP from Backbone Measurements, IEEE INFOCOM 7, Anchorage, USA, 7. [18] SIPp Web Site: [19] J. Jamae, P. Johnson, JBoss in Action, Manning, 9. [20] C. Gourraud, Using IMS as a Service Framework, IEEE Vehicular Technology Magazine, March 7, pp [21] 3GPP TS IP Multimedia Subsystem (IMS) Charging (Release 8), V8.5.0, [22] Open Cloud Web Site, available at: [23] Amdocs Web Site, available at: Service-Platform/Pages/index.aspx. [24] M. Femminella, E. Maccherani, G. Reali, Performance Management of Java-based SIP Application Servers, IM 2011, Dublin, May [25] Khlifi H., Gregoire J.-C., IMS Application Servers: Roles, Requirements, and Implementation Technologies, Internet Computing, IEEE, May-June 8, Volume: 12, Issue: 3, pp [26] M. Femminella, R. Francescangeli, F. Giacinti, E. Maccherani, A. Parisi, G. Reali, Implementation of third party media server controller for IMS networks, MobiMedia 9, London, UK, September 9. [27] L. Kleinrock, "Queueing Systems, Volume I: Theory", J. Wiley&Sons,

Performance Management of Java-based SIP Application Servers

Performance Management of Java-based SIP Application Servers 12th IFIP/IEEE 1M 2011: Mini Conference Performance Management of Java-based SIP Application Servers Mauro Femminella, Emanuele Maccherani, Gianluca Reali Department of Electronic and Information Engineering,

More information

Enabling Java-based VoIP backend platforms through JVM performance tuning

Enabling Java-based VoIP backend platforms through JVM performance tuning Enabling Java-based VoIP backend platforms through JVM performance tuning (Bruno Van Den Bossche, Filip De Turck, April 3rd 2006) 3 April, 2006, 1 Outline Introduction Java 4 Telecom Evaluation Setup Hardware

More information

Extension of Resource Management in SIP

Extension of Resource Management in SIP Extension of Resource Management in SIP Franco Callegati and Aldo Campi University of Bologna, Italy {franco.callegati,aldo.campi}@unibo.it Abstract. In this work we discuss the issue of communication

More information

A Web Services based Architecture for NGN Services Delivery

A Web Services based Architecture for NGN Services Delivery A Web Services based Architecture for NGN Services Delivery K. Rezabeigi, A. Vafaei, N. Movahhedinia Abstract The notion of Next Generation Network (NGN) is based on the Network Convergence concept which

More information

SIP System Features. SIP Timer Values. Rules for Configuring the SIP Timers CHAPTER

SIP System Features. SIP Timer Values. Rules for Configuring the SIP Timers CHAPTER CHAPTER 4 Revised: March 24, 2011, This chapter describes features that apply to all SIP system operations. It includes the following topics: SIP Timer Values, page 4-1 SIP Session Timers, page 4-7 Limitations

More information

Support of parallel BPEL activities for the TeamCom Service Creation Platform for Next Generation Networks

Support of parallel BPEL activities for the TeamCom Service Creation Platform for Next Generation Networks Support of parallel BPEL activities for the TeamCom Service Creation Platform for Next Generation Networks T.Eichelmann 1, 2, W.Fuhrmann 3, U.Trick 1, B.Ghita 2 1 Research Group for Telecommunication Networks,

More information

SIP SERVICES USING SIP SERVLET API THE INFOLINE SERVICE

SIP SERVICES USING SIP SERVLET API THE INFOLINE SERVICE Journal of Information, Control and Management Systems, Vol. 8, (2010), No.3 SIP SERVICES USING SIP SERVLET API THE INFOLINE SERVICE Pavel SEGEČ University of Žilina, Faculty of Management Science and

More information

4.2 IMS Service Creation

4.2 IMS Service Creation 4.2 IMS Service Creation 63 IMS service layer application servers IMS basic telephony Simulation servers Subscriber data HSS -AS #1 -AS #2 MMTel application servers Cx IP access network Gm P-CSCF Mw S-CSCF

More information

Diplomado Certificación

Diplomado Certificación Diplomado Certificación Duración: 250 horas. Horario: Sabatino de 8:00 a 15:00 horas. Incluye: 1. Curso presencial de 250 horas. 2.- Material oficial de Oracle University (e-kit s) de los siguientes cursos:

More information

Overview of the Session Initiation Protocol

Overview of the Session Initiation Protocol CHAPTER 1 This chapter provides an overview of SIP. It includes the following sections: Introduction to SIP, page 1-1 Components of SIP, page 1-2 How SIP Works, page 1-3 SIP Versus H.323, page 1-8 Introduction

More information

Measuring MPLS overhead

Measuring MPLS overhead Measuring MPLS overhead A. Pescapè +*, S. P. Romano +, M. Esposito +*, S. Avallone +, G. Ventre +* * ITEM - Laboratorio Nazionale CINI per l Informatica e la Telematica Multimediali Via Diocleziano, 328

More information

VoIP Basics. 2005, NETSETRA Corporation Ltd. All rights reserved.

VoIP Basics. 2005, NETSETRA Corporation Ltd. All rights reserved. VoIP Basics Phone Network Typical SS7 Network Architecture What is VoIP? (or IP Telephony) Voice over IP (VoIP) is the transmission of digitized telephone calls over a packet switched data network (like

More information

RESTCOMMONE. SIP Servlets. Copyright All Rights Reserved Page 2

RESTCOMMONE. SIP Servlets. Copyright All Rights Reserved Page 2 RESTCOMMONE SIP Servlets Copyright All Rights Reserved Page 2 RestcommONE Core Components RestcommOne Connect Visual Designer Web Browser WebRTC SDK s Mobile WebRTC SDK s RESTful API Layer RestcommOne

More information

Kernel Korner AEM: A Scalable and Native Event Mechanism for Linux

Kernel Korner AEM: A Scalable and Native Event Mechanism for Linux Kernel Korner AEM: A Scalable and Native Event Mechanism for Linux Give your application the ability to register callbacks with the kernel. by Frédéric Rossi In a previous article [ An Event Mechanism

More information

Department of Computer Science. Burapha University 6 SIP (I)

Department of Computer Science. Burapha University 6 SIP (I) Burapha University ก Department of Computer Science 6 SIP (I) Functionalities of SIP Network elements that might be used in the SIP network Structure of Request and Response SIP messages Other important

More information

White Paper. Major Performance Tuning Considerations for Weblogic Server

White Paper. Major Performance Tuning Considerations for Weblogic Server White Paper Major Performance Tuning Considerations for Weblogic Server Table of Contents Introduction and Background Information... 2 Understanding the Performance Objectives... 3 Measuring your Performance

More information

Netaxis Solutions SIGMA

Netaxis Solutions SIGMA Netaxis Solutions SIGMA Product Description 14/04/2018 Page 1 of 13 Contact All enquiries related to the features described in this document can be emailed to support@netaxis.be. 14/04/2018 Page 2 of 13

More information

BT SIP Trunk Configuration Guide

BT SIP Trunk Configuration Guide CUCM 9.1 BT SIP Trunk Configuration Guide This document covers service specific configuration required for interoperability with the BT SIP Trunk service. Anything which could be considered as normal CUCM

More information

OO Based Development of a Multi Media Application Server Prototype

OO Based Development of a Multi Media Application Server Prototype OO Based Development of a Multi Media Application Prototype E. GUL, G. WILLEKENS(team leader), F.HOSTE, T. BATSELE, R. SELDERSLAGHS, N. QUARTIER Alcatel Bell (A7) Francis Wellesplein 1 2018 Antwerpen,

More information

SPECjAppServer2002 Statistics. Methodology. Agenda. Tuning Philosophy. More Hardware Tuning. Hardware Tuning.

SPECjAppServer2002 Statistics. Methodology. Agenda. Tuning Philosophy. More Hardware Tuning. Hardware Tuning. Scaling Up the JBoss Application Server. Peter Johnson JBoss World 2005 March 1, 2005 Conclusion Configuration. 8-CPU ES7000 (32-bit) SPECjAppServer 2002 JBoss Application Server 3.2.6 Unisys JVM 1.4.1_07

More information

VoIP Protocols and QoS

VoIP Protocols and QoS Announcements I. Times have been posted for demo slots VoIP Protocols and QoS II. HW5 and HW6 solutions have been posted HW6 being graded Internet Protocols CSC / ECE 573 Fall, 2005 N. C. State University

More information

Performance Best Practices Paper for IBM Tivoli Directory Integrator v6.1 and v6.1.1

Performance Best Practices Paper for IBM Tivoli Directory Integrator v6.1 and v6.1.1 Performance Best Practices Paper for IBM Tivoli Directory Integrator v6.1 and v6.1.1 version 1.0 July, 2007 Table of Contents 1. Introduction...3 2. Best practices...3 2.1 Preparing the solution environment...3

More information

The Session Initiation Protocol

The Session Initiation Protocol The Session Initiation Protocol N. C. State University CSC557 Multimedia Computing and Networking Fall 2001 Lecture # 25 Roadmap for Multimedia Networking 2 1. Introduction why QoS? what are the problems?

More information

Dialogic PowerMedia Media Resource Broker (MRB)

Dialogic PowerMedia Media Resource Broker (MRB) Dialogic PowerMedia Media Resource Broker (MRB) The PowerMedia Media Resource Broker (MRB), a standardscompliant, software-based Media Resource Broker that allows application developers, service providers

More information

Adding Telephony to Java Technology-Based Enterprise Applications

Adding Telephony to Java Technology-Based Enterprise Applications Adding Telephony to Java Technology-Based Enterprise Applications Jonathan Kaplan & Sreeram Duvur Researcher/Architect Sun Microsystems, Inc. http://glassfish.dev.java.net/ TS-4919 2007 JavaOne SM Conference

More information

SIP System Features. SIP Timer Values. Rules for Configuring the SIP Timers CHAPTER

SIP System Features. SIP Timer Values. Rules for Configuring the SIP Timers CHAPTER CHAPTER 4 Revised: October 30, 2012, This chapter describes features that apply to all SIP system operations. It includes the following topics: SIP Timer Values, page 4-1 Limitations on Number of URLs,

More information

Voice over IP Consortium

Voice over IP Consortium Voice over IP Consortium Version 1.6 Last Updated: August 20, 2010 121 Technology Drive, Suite 2 University of New Hampshire Durham, NH 03824 Research Computing Center Phone: +1-603-862-0186 Fax: +1-603-862-4181

More information

IMS Adoption Fueled by the Open IMS Core Project and MySQL

IMS Adoption Fueled by the Open IMS Core Project and MySQL IMS Adoption Fueled by the Open IMS Core Project and MySQL Overview The project was launched in 2006 to promote IMS (IP Multimedia Subsystem) technology adoption in next-generation telecommunications networks,

More information

Dialogic PowerMedia Media Resource Broker (MRB)

Dialogic PowerMedia Media Resource Broker (MRB) Dialogic PowerMedia Media Resource Broker (MRB) The PowerMedia Media Resource Broker (MRB) is a standardscompliant, software-based Media Resource Broker that allows application developers, service providers

More information

Extending SIP for QoS support

Extending SIP for QoS support Extending for QoS support D. Papalilo 1, S. Salsano 2, L. Veltri 3 1 Università di Roma La Sapienza (Italy) 2 DIE Università di Roma Tor Vergata (Italy) 3 CoRiTeL Via Anagnina 203, 00040 Roma (Italy) e-mail:

More information

Sonus Networks engaged Miercom to evaluate the call handling

Sonus Networks engaged Miercom to evaluate the call handling Key findings and conclusions: Lab Testing Summary Report September 2010 Report 100914B Product Category: Session Border Controller Vendor Tested: Sonus SBC 5200 successfully registered 256,000 user authenticated

More information

RSVP and the Integrated Services Architecture for the Internet

RSVP and the Integrated Services Architecture for the Internet RSVP and the Integrated Services Architecture for the Internet N. C. State University CSC557 Multimedia Computing and Networking Fall 2001 Lecture # 20 Roadmap for Multimedia Networking 2 1. Introduction

More information

Final Implemented QoS architecture for the IST Project VIRTUOUS Demonstrator

Final Implemented QoS architecture for the IST Project VIRTUOUS Demonstrator Final Implemented QoS architecture for the IST Project VIRTUOUS Demonstrator Filomena Del Sorbo, Giuseppe Lombardi, Fabio Ventrone Computer Science Department University of Rome La Sapienza, Via F. Buonarroti,

More information

X-Communicator: Implementing an advanced adaptive SIP-based User Agent for Multimedia Communication

X-Communicator: Implementing an advanced adaptive SIP-based User Agent for Multimedia Communication X-Communicator: Implementing an advanced adaptive SIP-based User Agent for Multimedia Communication Shakil Siddique, Raimund K. Ege and S. Masoud Sadjadi School of Computer Science Florida International

More information

Evaluation of Media Server in SIP-Based Voice Conferencing

Evaluation of Media Server in SIP-Based Voice Conferencing International Journal of Computer Theory and Engineering, Vol. 5, No. 4, August 13 Evaluation of Media Server in SIP-Based Voice Conferencing Fatemeh Samsami and Ahmad Akbari evaluations[2]-[7]. M. Ahmed

More information

ABC SBC: Secure Peering. FRAFOS GmbH

ABC SBC: Secure Peering. FRAFOS GmbH ABC SBC: Secure Peering FRAFOS GmbH Introduction While an increasing number of operators have already replaced their SS7 based telecommunication core network with a SIP based solution, the interconnection

More information

JVM Performance Study Comparing Java HotSpot to Azul Zing Using Red Hat JBoss Data Grid

JVM Performance Study Comparing Java HotSpot to Azul Zing Using Red Hat JBoss Data Grid JVM Performance Study Comparing Java HotSpot to Azul Zing Using Red Hat JBoss Data Grid Legal Notices JBoss, Red Hat and their respective logos are trademarks or registered trademarks of Red Hat, Inc.

More information

Runtime Application Self-Protection (RASP) Performance Metrics

Runtime Application Self-Protection (RASP) Performance Metrics Product Analysis June 2016 Runtime Application Self-Protection (RASP) Performance Metrics Virtualization Provides Improved Security Without Increased Overhead Highly accurate. Easy to install. Simple to

More information

IMS Bench SIPp. Introduction. Table of contents

IMS Bench SIPp. Introduction. Table of contents Introduction by David Verbeiren (Intel), Philippe Lecluse (Intel), Xavier Simonart (Intel) Table of contents 1 Overview... 2 2 Getting IMS Bench SIPp...3 3 Tested Platforms...3 4 Design Objectives...3

More information

Proposal Architecture For Quality of Service Provisioning Within Inter-domain IP Multimedia Subsystem Context

Proposal Architecture For Quality of Service Provisioning Within Inter-domain IP Multimedia Subsystem Context Proposal Architecture For Quality of Service Provisioning Within Inter-domain IP Multimedia Subsystem Context Mosbah Ageal Computer Engineering Department, Higher Polytechnic Institute of Zliten, Zliten,

More information

Chapter 4. Routers with Tiny Buffers: Experiments. 4.1 Testbed experiments Setup

Chapter 4. Routers with Tiny Buffers: Experiments. 4.1 Testbed experiments Setup Chapter 4 Routers with Tiny Buffers: Experiments This chapter describes two sets of experiments with tiny buffers in networks: one in a testbed and the other in a real network over the Internet2 1 backbone.

More information

Overview of SIP. Information About SIP. SIP Capabilities. This chapter provides an overview of the Session Initiation Protocol (SIP).

Overview of SIP. Information About SIP. SIP Capabilities. This chapter provides an overview of the Session Initiation Protocol (SIP). This chapter provides an overview of the Session Initiation Protocol (SIP). Information About SIP, page 1 How SIP Works, page 4 How SIP Works with a Proxy Server, page 5 How SIP Works with a Redirect Server,

More information

Voice over IP (VoIP)

Voice over IP (VoIP) Voice over IP (VoIP) David Wang, Ph.D. UT Arlington 1 Purposes of this Lecture To present an overview of Voice over IP To use VoIP as an example To review what we have learned so far To use what we have

More information

A Bandwidth-Broker Based Inter-Domain SLA Negotiation

A Bandwidth-Broker Based Inter-Domain SLA Negotiation A Bandwidth-Broker Based Inter-Domain SLA Negotiation Haci A. Mantar θ, Ibrahim T. Okumus, Junseok Hwang +, Steve Chapin β θ Department of Computer Engineering, Gebze Institute of Technology, Turkey β

More information

IP Multimedia Subsystem Application Servers

IP Multimedia Subsystem Application Servers IP Multimedia Subsystem Application Servers Second part of the project Presented by: Masood Khosroshahy B E G I N N I N G 1 June 2006 Project supervisor: Prof. Elie Najm IMS Application Servers HSS IMS

More information

Medical Sensor Application Framework Based on IMS/SIP Platform

Medical Sensor Application Framework Based on IMS/SIP Platform Medical Sensor Application Framework Based on IMS/SIP Platform I. Markota, I. Ćubić Research & Development Centre, Ericsson Nikola Tesla d.d. Poljička cesta 39, 21000 Split, Croatia Phone: +38521 305 656,

More information

Analyzing the Internal Processing of IMS-based and traditional VoIP systems

Analyzing the Internal Processing of IMS-based and traditional VoIP systems Analyzing the Internal Processing of IMS-based and traditional VoIP systems Yuheng He 1, Johannes Veerkamp 1, Attila Bilgic 1,2 1 Institute for Integrated Systems, Ruhr University Bochum, 44780 Bochum,

More information

Configuring SIP Registration Proxy on Cisco UBE

Configuring SIP Registration Proxy on Cisco UBE The Support for SIP Registration Proxy on Cisco UBE feature provides support for sending outbound registrations from Cisco Unified Border Element (UBE) based on incoming registrations. This feature enables

More information

IP Multimedia Subsystem Part 5 Marek Średniawa

IP Multimedia Subsystem Part 5 Marek Średniawa IP Multimedia Subsystem Part 5 Marek Średniawa mareks@tele.pw.edu.pl Institute of Telecommunications Project is co-financed by European Union within the European Social Fund 1 Identification in IMS Identities

More information

J2EE: Best Practices for Application Development and Achieving High-Volume Throughput. Michael S Pallos, MBA Session: 3567, 4:30 pm August 11, 2003

J2EE: Best Practices for Application Development and Achieving High-Volume Throughput. Michael S Pallos, MBA Session: 3567, 4:30 pm August 11, 2003 J2EE: Best Practices for Application Development and Achieving High-Volume Throughput Michael S Pallos, MBA Session: 3567, 4:30 pm August 11, 2003 Agenda Architecture Overview WebSphere Application Server

More information

Converged Networks. Objectives. References

Converged Networks. Objectives. References Converged Networks Professor Richard Harris Objectives You will be able to: Discuss what is meant by convergence in the context of current telecommunications terminology Provide a network architecture

More information

Performance Testing of Open Source IP Multimedia Subsystem

Performance Testing of Open Source IP Multimedia Subsystem Performance Testing of Open Source IP Multimedia Subsystem MATEJ KAVACKÝ Institute of Multimedia Information and Communication Technologies Faculty of Electrical Engineering and Information Technology,

More information

CDCS: a New Case-Based Method for Transparent NAT Traversals of the SIP Protocol

CDCS: a New Case-Based Method for Transparent NAT Traversals of the SIP Protocol CDCS: a New Case-Based Method for Transparent NAT Traversals of the SIP Protocol Mustapha GUEZOURI LISSI/SCTIC, University of Paris XII-Val de Marne, France e-mail mguezouri@yahoo.fr and Abdelhamid MELLOUK

More information

Performance Analysis: Impact of Signalling Load over IMS Core on KPIs

Performance Analysis: Impact of Signalling Load over IMS Core on KPIs Performance Analysis: Impact of Signalling Load over IMS Core on KPIs JIRI HOSEK, LUBOS NAGY, VIT NOVOTNY, PAVEL MASEK, and DOMINIK KOVAC Brno University of Technology, Department of Telecommunications,

More information

An Efficient NAT Traversal for SIP and Its Associated Media sessions

An Efficient NAT Traversal for SIP and Its Associated Media sessions An Efficient NAT Traversal for SIP and Its Associated Media sessions Yun-Shuai Yu, Ce-Kuen Shieh, *Wen-Shyang Hwang, **Chien-Chan Hsu, **Che-Shiun Ho, **Ji-Feng Chiu Department of Electrical Engineering,

More information

Telecommunication Services Engineering Lab. Roch H. Glitho

Telecommunication Services Engineering Lab. Roch H. Glitho 1 2 Outline 1. Introduction 2. Core SIP 3. Selected Extensions 3 Introduction: Signaling vs Media Signaling: Session establishment Session tear down Changes to the session Supplementary services Media:

More information

6WINDGate. White Paper. Packet Processing Software for Wireless Infrastructure

6WINDGate. White Paper. Packet Processing Software for Wireless Infrastructure Packet Processing Software for Wireless Infrastructure Last Update: v1.0 - January 2011 Performance Challenges for Wireless Networks As advanced services proliferate and video consumes an ever-increasing

More information

Low pass filter/over drop avoidance (LPF/ODA): an algorithm to improve the response time of RED gateways

Low pass filter/over drop avoidance (LPF/ODA): an algorithm to improve the response time of RED gateways INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS Int. J. Commun. Syst. 2002; 15:899 906 (DOI: 10.1002/dac.571) Low pass filter/over drop avoidance (LPF/ODA): an algorithm to improve the response time of

More information

About Terracotta Ehcache. Version 10.1

About Terracotta Ehcache. Version 10.1 About Terracotta Ehcache Version 10.1 October 2017 This document applies to Terraco a Ehcache Version 10.1 and to all subsequent releases. Specifications contained herein are subject to change and these

More information

Performance and Evaluation of Integrated Video Transmission and Quality of Service for internet and Satellite Communication Traffic of ATM Networks

Performance and Evaluation of Integrated Video Transmission and Quality of Service for internet and Satellite Communication Traffic of ATM Networks Performance and Evaluation of Integrated Video Transmission and Quality of Service for internet and Satellite Communication Traffic of ATM Networks P. Rajan Dr. K.L.Shanmuganathan Research Scholar Prof.

More information

INSE 7110 Winter 2009 Value Added Services Engineering in Next Generation Networks Week #2. Roch H. Glitho- Ericsson/Concordia University

INSE 7110 Winter 2009 Value Added Services Engineering in Next Generation Networks Week #2. Roch H. Glitho- Ericsson/Concordia University INSE 7110 Winter 2009 Value Added Services Engineering in Next Generation Networks Week #2 1 Outline 1. Basics 2. Media Handling 3. Quality of Service (QoS) 2 Basics - Definitions - History - Standards.

More information

CUCM 10.5 / CUBE 9.5. BT SIP Trunk Configuration Guide. 1 BT SIP Trunk Configuration Guide

CUCM 10.5 / CUBE 9.5. BT SIP Trunk Configuration Guide. 1 BT SIP Trunk Configuration Guide 1 BT SIP Trunk Configuration Guide CUCM 10.5 / CUBE 9.5 BT SIP Trunk Configuration Guide This document covers service specific configuration required for interoperability with the BT SIP Trunk service.

More information

TSIN02 - Internetworking

TSIN02 - Internetworking Lecture 8: SIP and H323 Litterature: 2004 Image Coding Group, Linköpings Universitet Lecture 8: SIP and H323 Goals: After this lecture you should Understand the basics of SIP and it's architecture Understand

More information

Analyzing the Receiver Window Modification Scheme of TCP Queues

Analyzing the Receiver Window Modification Scheme of TCP Queues Analyzing the Receiver Window Modification Scheme of TCP Queues Visvasuresh Victor Govindaswamy University of Texas at Arlington Texas, USA victor@uta.edu Gergely Záruba University of Texas at Arlington

More information

Dialogic PowerMedia IP Media Server

Dialogic PowerMedia IP Media Server The Dialogic PowerMedia IP Media Server is a robust softwarebased multimedia server that allows service providers to rapidly deliver cost-effective video solutions with a high-quality user experience over

More information

Application Management Webinar. Daniela Field

Application Management Webinar. Daniela Field Application Management Webinar Daniela Field Agenda } Agile Deployment } Project vs Node Security } Deployment } Cloud Administration } Monitoring } Logging } Alerting Cloud Overview Cloud Overview Project

More information

SIP Flex Test Suite. Highlights. IMS and VoIP Network Element and Service Testing

SIP Flex Test Suite. Highlights. IMS and VoIP Network Element and Service Testing SIP Flex Test Suite IMS and VoIP Network Element and Service Testing Highlights Feature, negative, load, regression, interoperability and scalability testing Negative and proprietary messages and call

More information

IP SLAs Overview. Finding Feature Information. Information About IP SLAs. IP SLAs Technology Overview

IP SLAs Overview. Finding Feature Information. Information About IP SLAs. IP SLAs Technology Overview This module describes IP Service Level Agreements (SLAs). IP SLAs allows Cisco customers to analyze IP service levels for IP applications and services, to increase productivity, to lower operational costs,

More information

to pay for it) has been waning. The Internet further changed the game.

to pay for it) has been waning. The Internet further changed the game. As the old telephone business models break down and new service paradigm takes over, communication companies must combine voice with the new services of the network. The SCI-Platform (Service Convergence

More information

Location Based Advanced Phone Dialer. A mobile client solution to perform voice calls over internet protocol. Jorge Duda de Matos

Location Based Advanced Phone Dialer. A mobile client solution to perform voice calls over internet protocol. Jorge Duda de Matos Location Based Advanced Phone Dialer A mobile client solution to perform voice calls over internet protocol Jorge Duda de Matos Superior Institute of Technology (IST) Lisbon, Portugal Abstract Mobile communication

More information

IPv6-based Beyond-3G Networking

IPv6-based Beyond-3G Networking IPv6-based Beyond-3G Networking Motorola Labs Abstract This paper highlights the technical issues in IPv6-based Beyond-3G networking as a means to enable a seamless mobile Internet beyond simply wireless

More information

Fault Management for VoIP Applications over wireless and wired NGN Networks: an operational prospective

Fault Management for VoIP Applications over wireless and wired NGN Networks: an operational prospective 7th IEEE International Workshop on Performance and Management of Wireless and Mobile Networks P2MNET 2011, Bonn, Germany Fault Management for VoIP Applications over wireless and wired NGN Networks: an

More information

Mohammad Hossein Manshaei 1393

Mohammad Hossein Manshaei 1393 Mohammad Hossein Manshaei manshaei@gmail.com 1393 Voice and Video over IP Slides derived from those available on the Web site of the book Computer Networking, by Kurose and Ross, PEARSON 2 Multimedia networking:

More information

IMC Network Traffic Analyzer 7.3 (E0504) Copyright 2015, 2017 Hewlett Packard Enterprise Development LP

IMC Network Traffic Analyzer 7.3 (E0504) Copyright 2015, 2017 Hewlett Packard Enterprise Development LP Network Traffic Analyzer 7.3 (E0504) Copyright 2015, 2017 Hewlett Packard Enterprise Development LP Table of Contents 1. What's New in this Release 2. Problems Fixed in this Release 3. Software Distribution

More information

Delayed ACK Approach for TCP Performance Improvement for Ad Hoc Networks Using Chain Topology

Delayed ACK Approach for TCP Performance Improvement for Ad Hoc Networks Using Chain Topology Delayed ACK Approach for TCP Performance Improvement for Ad Hoc Networks Using Chain Topology Prashant Kumar Gupta M.Tech. Scholar, Computer Networks, Bhilai Institute of Technology, Durg (C.G.), India

More information

ETSI TS V1.1.1 ( )

ETSI TS V1.1.1 ( ) TS 183 028 V1.1.1 (2006-04) Technical Specification Telecommunications and Internet Converged Services and Protocols for Advanced Networking (TISPAN); Common basic communication procedures; Protocol specification

More information

Advanced VoIP Applications

Advanced VoIP Applications Advanced VoIP Applications New application deployments for VoIP networks can use a variety of network protocols and architectures. The use of MGCP and SIP are possible solutions and this paper discusses

More information

Quality of Service Mechanism for MANET using Linux Semra Gulder, Mathieu Déziel

Quality of Service Mechanism for MANET using Linux Semra Gulder, Mathieu Déziel Quality of Service Mechanism for MANET using Linux Semra Gulder, Mathieu Déziel Semra.gulder@crc.ca, mathieu.deziel@crc.ca Abstract: This paper describes a QoS mechanism suitable for Mobile Ad Hoc Networks

More information

Tuning and development with SIP Servlet on Mobicents. Naoki Nishihara OKI Electric Industry Co.,Ltd Jean Deruelle Mobicents Sip Servlets Lead

Tuning and development with SIP Servlet on Mobicents. Naoki Nishihara OKI Electric Industry Co.,Ltd Jean Deruelle Mobicents Sip Servlets Lead Tuning and development with SIP Servlet on Mobicents Naoki Nishihara OKI Electric Industry Co.,Ltd Jean Deruelle Mobicents Sip Servlets Lead Agenda Introduction SIP Application behavior How to tune the

More information

Interworking Signaling Enhancements for H.323 and SIP VoIP

Interworking Signaling Enhancements for H.323 and SIP VoIP Interworking Signaling Enhancements for H.323 and SIP VoIP This feature module describes enhancements to H.323 and Session Initiation Protocol (SIP) signaling when interworking with ISDN, T1 channel associated

More information

Installation & Configuration Guide Version 4.0

Installation & Configuration Guide Version 4.0 TekSIP Installation & Configuration Guide Version 4.0 Document Revision 6.8 https://www.kaplansoft.com/ TekSIP is built by Yasin KAPLAN Read Readme.txt for last minute changes and updates, which can be

More information

SIP System Features. Differentiated Services Codepoint CHAPTER

SIP System Features. Differentiated Services Codepoint CHAPTER CHAPTER 6 Revised: December 30 2007, This chapter describes features that apply to all SIP system operations. It includes the following topics: Differentiated Services Codepoint section on page 6-1 Limitations

More information

Service Execution Platform WebOTX To Support Cloud Computing

Service Execution Platform WebOTX To Support Cloud Computing Service Execution Platform WebOTX To Support Cloud Computing KATOU Masayuki Abstract The trend toward reductions in IT investments due to the current economic climate has tended to focus our attention

More information

Talkative Engage Mitel Architecture Guide. Version 1.0

Talkative Engage Mitel Architecture Guide. Version 1.0 Talkative Engage Mitel Architecture Guide Version 1.0 This document contains confidential information that is proprietary to Talkative. No part of its contents may be used, disclosed or conveyed to any

More information

Chapter 3: IP Multimedia Subsystems and Application-Level Signaling

Chapter 3: IP Multimedia Subsystems and Application-Level Signaling Chapter 3: IP Multimedia Subsystems and Application-Level Signaling Jyh-Cheng Chen and Tao Zhang IP-Based Next-Generation Wireless Networks Published by John Wiley & Sons, Inc. January 2004 Outline 3.1

More information

The Client Server Model and Software Design

The Client Server Model and Software Design The Client Server Model and Software Design Prof. Chuan-Ming Liu Computer Science and Information Engineering National Taipei University of Technology Taipei, TAIWAN MCSE Lab, NTUT, TAIWAN 1 Introduction

More information

Session Initiation Protocol (SIP)

Session Initiation Protocol (SIP) Session Initiation Protocol (SIP) Introduction A powerful alternative to H.323 More flexible, simpler Easier to implement Advanced features Better suited to the support of intelligent user devices A part

More information

This is a sample chapter of WebRTC: APIs and RTCWEB Protocols of the HTML5 Real-Time Web by Alan B. Johnston and Daniel C. Burnett.

This is a sample chapter of WebRTC: APIs and RTCWEB Protocols of the HTML5 Real-Time Web by Alan B. Johnston and Daniel C. Burnett. This is a sample chapter of WebRTC: APIs and RTCWEB Protocols of the HTML5 Real-Time Web by Alan B. Johnston and Daniel C. Burnett. For more information or to buy the paperback or ebook editions, visit

More information

TransferHTTP+CAS: Latency and Memory Tests

TransferHTTP+CAS: Latency and Memory Tests TransferHTTP+CAS: Latency and Memory Tests 1 Michael Adeyeye, 2 Neco Ventura 1 Department of Information Technology, Cape Peninsula University of Technology, Cape Town adeyeyem@cput.ac.za 2 Communication

More information

Forschungszentrum Telekommunikation Wien. OpenSER IMS. Joachim Fabini Institute of Broadband Communications Vienna University of Technology

Forschungszentrum Telekommunikation Wien. OpenSER IMS. Joachim Fabini Institute of Broadband Communications Vienna University of Technology Forschungszentrum Telekommunikation Wien OpenSER IMS Joachim Fabini Institute of Broadband Communications Vienna University of Technology Agenda IMS-related projects at ftw. CAMPARI IMS Testbed Architecture

More information

[MS-TURNBWM]: Traversal using Relay NAT (TURN) Bandwidth Management Extensions

[MS-TURNBWM]: Traversal using Relay NAT (TURN) Bandwidth Management Extensions [MS-TURNBWM]: Traversal using Relay NAT (TURN) Bandwidth Management Extensions Intellectual Property Rights Notice for Open Specifications Documentation Technical Documentation. Microsoft publishes Open

More information

SIPCache: A Distributed SIP Location Service for Mobile Ad-Hoc Networks

SIPCache: A Distributed SIP Location Service for Mobile Ad-Hoc Networks SIPCache: A Distributed SIP Location Service for Mobile Ad-Hoc Networks Simone Leggio Hugo Miranda Kimmo Raatikainen Luís Rodrigues University of Helsinki University of Lisbon August 16, 2006 Abstract

More information

Experimental Extensions to RSVP Remote Client and One-Pass Signalling

Experimental Extensions to RSVP Remote Client and One-Pass Signalling 1 Experimental Extensions to RSVP Remote Client and One-Pass Signalling Industrial Process and System Communications, Darmstadt University of Technology Merckstr. 25 D-64283 Darmstadt Germany Martin.Karsten@KOM.tu-darmstadt.de

More information

Service Initiation Procedure with On-demand UE Registration for Scalable IMS Services

Service Initiation Procedure with On-demand UE Registration for Scalable IMS Services Service Initiation Procedure with On-demand UE Registration for Scalable IMS Services Y. Kitatsuji, Y. Noishiki, M. Itou and H. Yokota KDDI R&D Laboratories, Inc. 2-1-15, Ohara, Fujimino, Saitama, 356-8502,

More information

Mobile SCTP for IP Mobility Support in All-IP Networks

Mobile SCTP for IP Mobility Support in All-IP Networks Mobile SCTP for IP Mobility Support in All-IP Networks Seok Joo Koh sjkoh@cs.knu.ac.kr Abstract The Stream Control Transmission Protocol (SCTP) is a new transport protocol that is featured multi-streaming

More information

Lecture 7: February 10

Lecture 7: February 10 CMPSCI 677 Operating Systems Spring 2016 Lecture 7: February 10 Lecturer: Prashant Shenoy Scribe: Tao Sun 7.1 Server Design Issues 7.1.1 Server Design There are two types of server design choices: Iterative

More information

Oracle Communications WebRTC Session Controller

Oracle Communications WebRTC Session Controller Oracle Communications WebRTC Session Controller Concepts Release 7.0 E40976-01 November 2013 Oracle Communications WebRTC Session Controller Concepts, Release 7.0 E40976-01 Copyright 2013, Oracle and/or

More information

Domain Based Approach for QoS Provisioning in Mobile IP

Domain Based Approach for QoS Provisioning in Mobile IP Domain Based Approach for QoS Provisioning in Mobile IP Ki-Il Kim and Sang-Ha Kim Department of Computer Science 220 Gung-dong,Yuseong-gu, Chungnam National University, Deajeon 305-764, Korea {kikim, shkim}@cclab.cnu.ac.kr

More information

Oracle Event Processing Extreme Performance on Sparc T5

Oracle Event Processing Extreme Performance on Sparc T5 Oracle Event Processing Extreme Performance on Sparc T5 An Oracle Event Processing (OEP) Whitepaper ORACLE WHITE PAPER AUGUST 2014 Table of Contents Introduction 2 OEP Architecture 2 Server Architecture

More information

Flash: an efficient and portable web server

Flash: an efficient and portable web server Flash: an efficient and portable web server High Level Ideas Server performance has several dimensions Lots of different choices on how to express and effect concurrency in a program Paper argues that

More information