Οι οικονομικές και τεχνολογικές εξελίξεις των τελευταίων ετών, η απελευθέρωση της αγοράς, οι ισχυρές κατά απαίτηση πολυμεσικές υπηρεσίες καθώς και ο αυξημένος αριθμός χρηστών των κινητών δικτύων υποδεικνύουν την αναγκαιότητα της σύγκλισης των δύο δικτυακών τεχνολογιών (κινητή τηλεφωνία και internet) με στόχο την παροχή υπηρεσιών Internet στο περιβάλλον των κινητών επικοινωνιών. Η παραπάνω απαίτηση οδήγησε στην δημιουργία του δικτύου επόμενης γενιάς NGN. Η διπλωματική αυτή εργασία ασχολείται με την μελέτη της αρχιτεκτονικής του επιπέδου υπηρεσιών και την υποστήριξη Ποιότητας Υπηρεσίας (QoS) σε δίκτυα Νέας Γενιάς. Συγκεκριμένα δίνεται έμφαση στις λειτουργίες ελέγχου, σηματοδοσίας και λειτουργιών αρχιτεκτονικής του QoS σε επίπεδο υπηρεσιών. Αρχικά, ορίζουμε την έννοια “QoS” όσον αφορά την οπτική του δικτύου και το χρήστη. Περιγράφονται η αρχιτεκτονική του στρώματος υπηρεσιών του δικτύου καθώς και οι λειτουργίες ελέγχου πόρου και αποδοχής των κλήσεων, που αποτελούν σημαντικό μέρος της αρχιτεκτονικής του NGN. Στη συνέχεια παρουσιάζονται αρχιτεκτονικές που προορίζονται για την παροχή του QoS (IntServ, DiffServ), στη Συμφωνία Στάθμης Παρεχόμενης Υπηρεσίας (SLA), το πρωτόκολλο σηματοδοσίας COPS. Επίσης, δίνουμε έμφαση σε ορισμένες πτυχές (χρονοδρομολόγηση, διαχείριση ουρών) μίας QoS αρχιτεκτονικής, οι οποίες είναι ζωτικής σημασίας όσον αφορά την αποδοτική παροχή Ποιότητας Υπηρεσίας. Στη συνέχεια, με τη χρήση του εργαλείου προσομοίωσης OPNET, διεξάγουμε μια σειρά προσομοιώσεων σε ένα ATM και σε ένα NGN δίκτυο. Τέλος, παραθέτουμε και αναλύουμε τα αποτελέσματα των προαναφερθέντων πειραμάτων. / The concept of an NGN (Next Generation Network) has been introduced to take into consideration the new realities in the telecommunications industry, characterized by factors such as: competition among operators due to ongoing deregulation of markets, explosion of digital traffic, e.g.,increasing use of "the Internet", increasing demand for new multimedia services, increasing demand for a general mobility, convergence of networks and services, etc. This thesis has as subject the architecture of service stratum and presents an overview of standards functions defining the Quality of Service (QoS) in Next Generation Networks (NGNs). Several standards bodies define the QoS control architectures based on their scope of work. Specifically, emphasis is given to control functions, signalling and functional architecture of QoS in service stratum. Firstly, we define the meaning of QoS according to the view of the operator’s network and terminal users. The functional architecture of service stratum and especially the part of resource and admission control functions are described in the main body. Furthermore, architectures as IntServ and DiffServ, SLAs and COPS protocol are used as providers of the QoS. Scheduling and queuing management are necessary to optimize the QoS in NGN networks. In this project, we use OPNET simulator in two scenarios to determine construct and control ATM and NGN networks. Finally, collect the results of the experiments and analyze them.

Network on Chips[1][2][3][4] are critical elements of modern System on Chip(SoC) as well as Chip Multiprocessor(CMP)designs. Network on Chips (NoCs) help manage high complexity of designing large chips by decoupling computation from communication. SoCs and CMPs have a multiplicity of communicating entities like programmable processing elements, hardware acceleration engines, memory blocks as well as off-chip interfaces. With power having become a serious design constraint[5], there is a great need for designing NoC which meets the target communication requirements, while minimizing power using all the tricks available at the architecture, microarchitecture and circuit levels of the de-sign. This thesis presents a holistic, QoS based, power optimal design solution of a NoC inside a CMP taking into account link microarchitecture and processor tile configurations. Guaranteeing QoS by NoCs involves guaranteeing bandwidth and throughput for connections and deterministic latencies in communication paths. Label Switching based Network-on-Chip(LS-NoC) uses a centralized LS-NoC Management framework that engineers traffic into QoS guaranteed routes. LS-NoC uses label switching, enables band-width reservation, allows physical link sharing and leverages advantages of both packet and circuit switching techniques. A flow identification algorithm takes into account band-width available in individual links to establish QoS guaranteed routes. LS-NoC caters to the requirements of streaming applications where communication channels are fixed over the lifetime of the application. The proposed NoC framework inherently supports heterogeneous and ad-hoc SoC designs. A multicast, broadcast capable label switched router for the LS-NoC has been de-signed, verified, synthesized, placed and routed and timing analyzed. A 5 port, 256 bit data bus, 4 bit label router occupies 0.431 mm2 in 130nm and delivers peak band-width of80Gbits/s per link at312.5MHz. LS Router is estimated to consume 43.08 mW. Bandwidth and latency guarantees of LS-NoC have been demonstrated on streaming applications like Hiper LAN/2 and Object Recognition Processor, Constant Bit Rate traffic patterns and video decoder traffic representing Variable Bit Rate traffic. LS-NoC was found to have a competitive figure of merit with state-of-the-art NoCs providing QoS. We envision the use of LS-NoC in general purpose CMPs where applications demand deterministic latencies and hard bandwidth requirements. Design variables for interconnect exploration include wire width, wire spacing, repeater size and spacing, degree of pipelining, supply, threshold voltage, activity and coupling factors. An optimal link configuration in terms of number of pipeline stages for a given length of link and desired operating frequency is arrived at. Optimal configurations of all links in the NoC are identified and a power-performance optimal NoC is presented. We presents a latency, power and performance trade-off study of NoCs using link microarchitecture exploration. The design and implementation of a framework for such a design space exploration study is also presented. We present the trade-off study on NoCs by varying microarchitectural(e.g. pipelining) and circuit level(e.g. frequency and voltage) parameters. A System-C based NoC exploration framework is used to explore impacts of various architectural and microarchitectural level parameters of NoC elements on power and performance of the NoC. The framework enables the designer to choose from a variety of architectural options like topology, routing policy, etc., as well as allows experimentation with various microarchitectural options for the individual links like length, wire width, pitch, pipelining, supply voltage and frequency. The framework also supports a flexible traffic generation and communication model. Latency, power and throughput results using this framework to study a 4x4 CMP are presented. The framework is used to study NoC designs of a CMP using different classes of parallel computing benchmarks[6]. One of the key findings is that the average latency of a link can be reduced by increasing pipeline depth to a certain extent, as it enables link operation at higher link frequencies. Abstract There exists an optimum degree of pipelining which minimizes the energy-delay product of the link. In a 2D Torus when the longest link is pipelined by 4 stages at which point least latency(1.56 times minimum) is achieved and power(40% of max) and throughput (64%of max) are nominal. Using frequency scaling experiments, power variations of up to40%,26.6% and24% can be seen in 2D Torus, Reduced 2D Torus and Tree based NoC between various pipeline configurations to achieve same frequency at constant voltages. Also in some cases, we find that switching to a higher pipelining configuration can actually help reduce power as the links can be designed with smaller repeaters. We also find that the overall performance of the ICNs is determined by the lengths of the links needed to support the communication patterns. Thus the mesh seems to perform the best amongst the three topologies(Mesh, Torus and Folded Torus) considered in case studies. The effects of communication overheads on performance, power and energy of a multiprocessor chip using L1,L2 cache sizes as primary exploration parameters using accurate interconnect, processor, on-chip and off-chip memory modelling are presented. On-chip and off-chip communication times have significant impact on execution time and the energy efficiency of CMPs. Large cache simply larger tile area that result in longer inter-tile communication link lengths and latencies, thus adversely impacting communication time. Smaller caches potentially have higher number of misses and frequent of off-tile communication. Energy efficient tile design is a configuration exploration and trade-off study using different cache sizes and tile areas to identify a power-performance optimal configuration for the CMP. Trade-offs are explored using a detailed, cycle accurate, multicore simulation frame-work which includes superscalar processor cores, cache coherent memory hierarchies, on-chip point-to-point communication networks and detailed interconnect model including pipelining and latency. Sapphire, a detailed multiprocessor execution environment integrating SESC, Ruby and DRAM Sim was used to run applications from the Splash2 benchmark(64KpointFFT).Link latencies are estimated for a16 core CMP simulation on Sapphire. Each tile has a single processor, L1 and L2 caches and a router. Different sizesofL1 andL2lead to different tile clock speeds, tile miss rates and tile area and hence interconnect latency. Simulations across various L1, L2 sizes indicate that the tile configuration that maximizes energy efficiency is related to minimizing communication time. Experiments also indicate different optimal tile configurations for performance, energy and energy efficiency. Clustered interconnection network, communication aware cache bank mapping and thread mapping to physical cores are also explored as potential energy saving solutions. Results indicate that ignoring link latencies can lead to large errors in estimates of program completion times, of up to 17%. Performance optimal configurations are achieved at lower L1 caches and at moderateL2 cache sizes due to higher operating frequencies and smaller link lengths and comparatively lesser communication. Using minimal L1 cache size to operate at the highest frequency may not always be the performance-power optimal choice. Larger L1 sizes, despite a drop in frequency, offer a energy advantage due to lesser communication due to misses. Clustered tile placement experiments for FFT show considerable performance per watt improvement (1.2%). Remapping most accessed L2 banks by a process in the same core or neighbouring cores after communication traffic analysis offers power and performance advantages. Remapped processes and banks in clustered tile placement show a performance per watt improvement of5.25% and energy reductionof2.53%. This suggests that processors could execute a program in multiple modes, for example, minimum energy, maximum performance.

Governments, military, corporations, financial institutions and others exchange a great deal of confidential information using Internet these days. Protecting such confidential information and ensuring their integrity and origin authenticity are of paramount importance. There exist protocols and solutions at different layers of the TCP/IP protocol stack to address these security requirements. Application level encryption viz. PGP for secure mail transfer, TLS based secure TCP communication, IPSec for providing IP layer security are among these security solutions. Due to scalability, wide acceptance of the IP protocol, and its application independent character, the IPSec protocol has become a standard for providing Internet security. The IPSec provides two protocols namely the Authentication header (AH) and the Encapsulating Security Payload (ESP). Each protocol can operate in two modes, viz. transport and tunnel mode. The AH provides data origin authentication, connectionless integrity and anti replay protection. The ESP provides all the security functionalities of AH along with confidentiality. The IPSec protocols provide end-to-end security for an entire IP datagram or the upper layer protocols of IP payload depending on the mode of operation. However, this end-to-end model of security restricts performance enhancement and security related operations of intermediate networking and security devices, as they can not access or modify transport and upper layer headers and original IP headers in case of tunnel mode. These intermediate devices include routers providing Quality of Service (QoS), TCP Performance Enhancement Proxies (PEP), Application level Proxy devices and packet filtering firewalls. The interoperability problem between IPSec and intermediate devices has been addressed in literature. Transport friendly ESP (TF-ESP), Transport Layer Security (TLS), splitting of single IPSec tunnel into multiple tunnels, Multi Layer IPSec (ML-IPSec) are a few of the proposed solutions. The ML-IPSec protocol solves this interoperability problem without violating the end-to-end security for the data or exposing some important header fields unlike the other solutions. The ML-IPSec uses a multilayer protection model in place of the single end-to-end model. Unlike IPSec where the scope of encryption and authentication applies to the entire IP datagram, this scheme divides the IP datagram into zones. It applies different protection schemes to different zones. When ML-IPSec protects a traffic stream from its source to its destination, it first partitions the IP datagram into zones and applies zone-specific cryptographic protections. During the flow of the ML-IPSec protected datagram through an authorized intermediate gateway, certain type I zones of the datagram may be decrypted and re-encrypted, but the other zones will remain untouched. When the datagram reaches its destination, the ML-IPSec will reconstruct the entire datagram. The ML-IPSec protocol, however suffers from the problem of static configuration of zones and zone specific cryptographic parameters before the commencement of the communication. Static configuration requires a priori knowledge of routing infrastructure and manual configuration of all intermediate nodes. While this may not be an issue in a geo-stationary satellite environment using TCP-PEP, it could pose problems in a mobile or distributed environment, where many stations may be in concurrent use. The ML-IPSec endpoints may not be trusted by all intermediate nodes in a mobile environment for manual configuration without any prior arrangement providing the mutual trust. The static zone boundary of the protocol forces one to ignore the presence of TCP/IP datagrams with variable header lengths (in case of TCP or IP headers with OPTION fields). Thus ML-IPSec will not function correctly if the endpoints change the use of IP or TCP options, especially in case of tunnel mode. The zone mapping proposed in ML-IPSec is static in nature. This forces one to configure the zone mapping before the commencement of the communication. It restricts the protocol from dynamically changing the zone mapping for providing access to intermediate nodes without terminating the existing ML-IPSec communication. The ML-IPSec endpoints can off course, configure the zone mapping with maximum number of zones. This will lead to unnecessary overheads that increase with the number of zones. Again, static zone mapping could pose problems in a mobile or distributed environment, where communication paths may change. Our extension to the ML-IPSec protocol, called Dynamic Multi Layer IPSec (DML-IPSec) proposes a multi layer variant with the capabilities of dynamic zone configuration and sharing of cryptographic parameters between IPSec endpoints and intermediate nodes. It also accommodates IP datagrams with variable length headers. The DML-IPSec protocol redefines some of the IPSec and ML-IPSec fundamentals. It proposes significant modifications to the datagram processing stage of ML-IPSec and proposes a new key sharing protocol to provide the above-mentioned capabilities. The DML-IPSec supports the AH and ESP protocols of the conventional IPSec with some modifications required for providing separate cryptographic protection to different zones of an IP datagram. This extended protocol defines zone as a set of non-overlapping and contiguous partitions of an IP datagram, unlike the case of ML-IPSec where a zone may consist of non-contiguous portions. Every zone is provided with cryptographic protection independent of other zones. The DML-IPSec categorizes zones into two separate types depending on the accessibility requirements at the intermediate nodes. The first type of zone, called type I zone, is defined on headers of IP datagram and is required for examination and modification by intermediate nodes. One type I zone may span over a single header or over a series of contiguous headers of an IP datagram. The second type of zone, called type II zone, is meant for the payload portion and is kept secure between endpoints of IPSec communications. The single type II zone starts immediately after the last type I zone and spans till the end of the IP datagram. If no intermediate processing is required during the entire IPSec session, the single type II zone may cover the whole IP datagram; otherwise the single type II zone follows one or more type I zones of the IP datagram. The DML-IPSec protocol uses a mapping from the octets of the IP datagram to different zones, called zone map for partitioning an IP datagram into zones. The zone map contains logical boundaries for the zones, unlike physical byte specific boundaries of ML-IPSec. The physical boundaries are derived on-the-fly, using either the implicit header lengths or explicit header length fields of the protocol headers. This property of the DML-IPSec zones, enables it to accommodate datagrams with variable header lengths. Another important feature of DML-IPSec zone is that the zone maps need not remain constant through out the entire lifespan of IPSec communication. The key sharing protocol may modify any existing zone map for providing service to some intermediate node. The DML-IPSec also redefines Security Association (SA), a relationship between two endpoints of IPSec communication that describes how the entities will use security services to communicate securely. In the case of DML-IPSec, several intermediate nodes may participate in defining these security protections to the IP datagrams. Moreover, the scope of one particular set of security protection is valid on a single zone only. So a single SA is defined for each zone of an IP datagram. Finally all these individual zonal SA’s are combined to represent the security relationship of the entire IP datagram. The intermediate nodes can have the cryptographic information of the relevant type I zones. The cryptographic information related to the type II zone is, however, hidden from any intermediate node. The key sharing protocol is responsible for selectively sharing this zone information with the intermediate nodes. The DML-IPSec protocol has two basic components. The first one is for processing of datagrams at the endpoints as well as intermediate nodes. The second component is the key sharing protocol. The endpoints of a DML-IPSec communication involves two types of processing. The first one, called Outbound processing, is responsible for generating a DML-IPSec datagram from an IP datagram. It first derives the zone boundaries using the zone map and individual header field lengths. After this partitioning of IP datagram, zone wise encryption is applied (in case of ESP). Finally zone specific authentication trailers are calculated and appended after each zone. The other one, Inbound processing, is responsible for generating the original IP datagram from a DML-IPSec datagram. The first step in the inbound processing, the derivation of zone boundary, is significantly different from that of outbound processing as the length fields of zones remain encrypted. After receiving a DML-IPSec datagram, the receiver starts decrypting type I zones till it decrypts the header length field of the header/s. This is followed by zone-wise authentication verification and zone-wise decryption. The intermediate nodes processes an incoming DML-IPSec datagram depending on the presence of the security parameters for that particular DML-IPSec communication. In the absence of the security parameters, the key sharing protocol gets executed; otherwise, all the incoming DML-IPSec datagrams get partially decrypted according to the security association and zone mapping at the inbound processing module. After the inbound processing, the partially decrypted IP datagram traverses through the networking stack of the intermediate node . Before the IP datagram leaves the intermediate node, it is processed by the outbound module to reconstruct the DML-IPSec datagram. The key sharing protocol for sharing zone related cryptographic information among the intermediate nodes is the other important component of the DML-IPSec protocol. This component is responsible for dynamically enabling intermediate nodes to access zonal information as required for performing specific services relating to quality or security. Whenever a DML-IPSec datagram traverses through an intermediate node, that requires access to some of the type I zones, the inbound security database is searched for cryptographic parameters. If no entry is present in the database, the key sharing protocol is invoked. The very first step in this protocol is a header inaccessible message from the intermediate node to the source of the DML-IPSec datagram. The intermediate node also mentions the protocol headers that it requires to access in the body portion of this message. This first phase of the protocol, called the Zone reorganization phase, is responsible for deciding the zone mapping to provide access to intermediate nodes. If the current zone map can not serve the header request, the DML-IPSec endpoint reorganizes the existing zone map in this phase. The next phase of the protocol, called the Authentication Phase is responsible for verifying the identity of the intermediate node to the source of DML-IPSec session. Upon successful authentication, the third phase, called the Shared secret establishment phase commences. This phase is responsible for the establishment of a temporary shared secret between the source and intermediate nodes. This shared secret is to be used as key for encrypting the actual message transfer of the DML-IPSec security parameters at the next phase of the protocol. The final phase of the protocol, called the Security parameter sharing phase, is solely responsible for actual transfer of the security parameters from the source to the intermediate nodes. This phase is also responsible for updation of security and policy databases of the intermediate nodes. The successful execution of the four phases of the key sharing protocol enables the DML-IPSec protocol to dynamically modify the zone map for providing access to some header portions for intermediate nodes and also to share the necessary cryptographic parameters required for accessing relevant type I zones without disturbing an existing DML-IPSec communication. We have implemented the DML-IPSec for ESP protocol according to the definition of zones along with the key sharing algorithm. RHEL version 4 and Linux kernel version 2.6.23.14 was used for the implementation. We implemented the multi-layer IPSec functionalities inside the native Linux implementation of IPSec protocol. The SA structure was updated to hold necessary SA information for multiple zones instead of single SA of the normal IPSec. The zone mapping for different zones was implemented along with the kernel implementation of SA. The inbound and outbound processing modules of the IPSec endpoints were re-implemented to incorporate multi-layer IPSec capability. We also implemented necessary modules for providing partial IPSec processing capabilities at the intermediate nodes. The key sharing protocol consists of some user space utilities and corresponding kernel space components. We use ICMP protocol for the communications required for the execution of the protocol. At the kernel level, pseudo character device driver was implemented to update the kernel space data structures and necessary modifications were made to relevant kernel space functions. User space utilities and corresponding kernel space interface were provided for updating the security databases. As DML-IPSec ESP uses same Security Policy mechanism as IPSec ESP, existing utilities (viz. setkey) are used for the updation of security policy. However, the configuration of the SA is significantly different as it depends on the DML-IPSec zones. The DML-IPSec ESP implementation uses the existing utilities (setkey and racoon) for configuration of the sole type II zone. The type I zones are configured using the DML-IPSec application. The key sharing protocol also uses this application to reorganize the zone mapping and zone-wise cryptographic parameters. The above feature enables one to use default IPSec mechanism for the configuration of the sole type II zone. For experimental validation of DML-IPSec, we used the testbed as shown in the above figure. An ESP tunnel is configured between the two gateways GW1 and GW2. IN acts as an intermediate node and is installed with several intermediate applications. Clients C11 and C21 are connected to GW1 and GW2 respectively. We carried out detailed experiments for validating our solution w.r.t firewalling service. We used stateful packet filtering using iptables along with string match extension at IN. First, we configured the firewall to allow only FTP communication (using port information of TCP header and IP addresses of Inner IP header ) between C11 and C21. In the second experiment, we configured the firewall to allow only Web connection between C11 and C21 using the Web address of C11 (using HTTP header, port information of TCP header and IP addresses of Inner IP header ). In both experiments, we initiated the FTP and WEB sessions before the execution of the key sharing protocol. The session could not be established as the access to upper layer headers was denied. After the execution of the key sharing protocol, the sessions could be established, showing the availability of protocol headers to the iptables firewall at IN following the successful key sharing. We use record route option of ping program to validate the claim of handling datagrams with variable header lengths. This option of ping program records the IP addresses of all the nodes traversed during a round trip path in the IP OPTION field. As we used ESP in tunnel mode between GW1 and GW2, the IP addresses would be recorded inside the encrypted Inner IP header. We executed ping between C11 and C21 and observed the record route output. Before the execution of the key sharing protocol, the IP addresses of IN were absent in the record route output. After the successful execution of key sharing protocol, the IP addresses for IN were present at the record route output. The DML-IPSec protocol introduces some processing overhead and also increases the datagram size as compared to IPSec and ML-IPSec. It increases the datagram size compared to the standard IPSec. However, this increase in IP datagram size is present in the case of ML-IPSec as well. The increase in IP datagram length depends on the number of zones. As the number of zone increases this overhead also increases. We obtain experimental results about the processing delay introduced by DML-IPSec processing. For this purpose, we executed ping program from C11 to C21 in the test bed setup for the following cases: 1.ML-IPSec with one type I and one type II zone and 2. DML-IPSec with one type I and one type II zone. We observe around 10% increase in RTT in DML-IPSec with two dynamic zones over that of ML-IPSec with two static zones. This overhead is due to on-the-fly derivation of the zone length and related processing. The above experiment analyzes the processing delay at the endpoints without intermediate processing. We also analyzed the effect of intermediate processing due to dynamic zones of DML-IPSec. We used iptables firewall in the above mentioned experiment. The RTT value for DML-IPSec with dynamic zones increases by less than 10% over that of ML-IPSec with static zones. To summarize our work, we have proposed an extension to the multilayer IPSec protocol, called Dynamic Multilayer IPSec (DML-IPSec). It is capable of dynamic modification of zones and sharing of cryptographic parameters between endpoints and intermediate nodes using a key sharing protocol. The DML-IPSec also accommodates datagrams with variable header lengths. The above mentioned features enable any intermediate node to dynamically access required header portions of any DML-IPSec protected datagrams. Consequently they make the DML-IPSec suited for providing IPSec over mobile and distributed networks. We also provide complete implementation of ESP protocol and provide experimental validation of our work. We find that our work provides the dynamic support for QoS and security services without any significant extra overhead compared to that of ML-IPSec. The thesis begins with an introduction to communication security requirements in TCP/IP networks. Chapter 2 provides an overview of communication security protocols at different layers. It also describes the details of IPSec protocol suite. Chapter 3 provides a study on the interoperability issues between IPSec and intermediate devices and discusses about different solutions. Our proposed extension to the ML-IPSec protocol, called Dynamic ML-IPSec(DML-IPSec) is presented in Chapter 4. The design and implementation details of DML-IPSec in Linux environment is presented in Chapter 5. It also provides experimental validation of the protocol. In Chapter 6, we summarize the research work, highlight the contributions of the work and discuss the directions for further research.

[ES] Una de las principales preocupaciones de los centros de datos actuales es maximizar la utilización de los servidores. En cada servidor se ejecutan simultáneamente varias aplicaciones para aumentar la eficiencia de los recursos. Sin embargo, las prestaciones dependen en gran medida de la proporción de recursos que recibe cada aplicación. El mayor número de núcleos (y de aplicaciones ejecutándose) con cada nueva generación de procesadores hace que crezca la preocupación por la interferencia en los recursos compartidos. Esta tesis se centra en mitigar la interferencia cuando diferentes aplicaciones se consolidan en un mismo procesador desde dos perspectivas: computación de alto rendimiento (HPC) y computación en la nube. En el contexto de HPC, esta tesis propone políticas de gestión para dos de los recursos más críticos: la caché de último nivel (LLC) y los núcleos del procesador. La LLC desempeña un papel clave en las prestaciones de los procesadores actuales al reducir considerablemente el número de accesos de alta latencia a memoria principal. Se proponen estrategias de particionado de la LLC tanto para cachés inclusivas como no inclusivas, ambos diseños presentes en los procesadores para servidores actuales. Para los esquemas, se detectan nuevos comportamientos problemáticos y se asigna un mayor espacio de caché a las aplicaciones que hacen mejor uso de este. En cuanto a los núcleos del procesador, muchas aplicaciones paralelas (como aplicaciones de grafos) no escalan bien con un mayor número de núcleos. Además, el planificador de Linux aplica una estrategia de tiempo compartido que no ofrece buenas prestaciones cuando se ejecutan aplicaciones de grafo. Para maximizar la utilización del sistema, esta tesis propone ejecutar múltiples aplicaciones de grafo en el mismo procesador, asignando a cada una el número óptimo de núcleos (y adaptando el número de hilos creados) dinámicamente. En cuanto a la computación en la nube, esta tesis aborda tres grandes retos: la compleja infraestructura de estos sistemas, las características de sus aplicaciones y el impacto de la interferencia entre máquinas virtuales (MV). Primero, esta tesis presenta la plataforma experimental desarrollada con los principales componentes de un sistema en la nube. Luego, se presenta un amplio estudio de caracterización sobre un conjunto de aplicaciones de latencia crítica representativas con el fin de identificar los puntos que los proveedores de servicios en la nube deben tener en cuenta para mejorar el rendimiento y la utilización de los recursos. Por último, se realiza una propuesta que permite detectar y estimar dinámicamente la interferencia entre MV. El enfoque usa métricas que pueden monitorizarse fácilmente en la nube pública, ya que las MV deben tratarse como "cajas negras". Toda la investigación descrita se lleva a cabo respetando las restricciones y cumpliendo los requisitos para ser aplicable en entornos de producción de nube pública. En resumen, esta tesis aborda la contención en los principales recursos compartidos del sistema en el contexto de la consolidación de servidores. Los resultados experimentales muestran importantes ganancias sobre Linux. En los procesadores con LLC inclusiva, el tiempo de ejecución (TT) se reduce en más de un 40%, mientras que se mejora el IPC más de un 3%. Con una LLC no inclusiva, la equidad y el TT mejoran en un 44% y un 24%, respectivamente, al mismo tiempo que se mejora el rendimiento hasta un 3,5%. Al distribuir los núcleos del procesador de forma eficiente, se alcanza una equidad casi perfecta (94%), y el TT se reduce hasta un 80%. En entornos de computación en la nube, la degradación del rendimiento puede estimarse con un error de un 5% en la predicción global. Todas las propuestas presentadas han sido diseñadas para ser aplicadas en procesadores comerciales sin requerir ninguna información previa, tomando las decisiones dinámicamente con datos recogidos de los contadores de prestaciones. / [CAT] Una de les principals preocupacions dels centres de dades actuals és maximitzar la utilització dels servidors. A cada servidor s'executen simultàniament diverses aplicacions per augmentar l'eficiència dels recursos. Tot i això, el rendiment depèn en gran mesura de la proporció de recursos que rep cada aplicació. El nombre creixent de nuclis (i aplicacions executant-se) amb cada nova generació de processadors fa que creixca la preocupació per l'efecte causat per les interferències en els recursos compartits. Aquesta tesi se centra a mitigar la interferència en els recursos compartits quan diferents aplicacions es consoliden en un mateix processador des de dues perspectives: computació d'alt rendiment (HPC) i computació al núvol. En el context d'HPC, aquesta tesi proposa polítiques de gestió per a dos dels recursos més crítics: la memòria cau d'últim nivell (LLC) i els nuclis del processador. La LLC exerceix un paper clau a les prestacions del sistema en els processadors actuals reduint considerablement el nombre d'accessos d'alta latència a la memòria principal. Es proposen estratègies de particionament de la LLC tant per a caus inclusives com no inclusives, ambdós dissenys presents en els processadors actuals. Per als dos esquemes, se detecten nous comportaments problemàtics i s'assigna un major espai de memòria cau a les aplicacions que en fan un millor ús. Pel que fa als nuclis del processador, moltes aplicacions paral·leles (com les aplicacions de graf) no escalen bé a mesura que s'incrementa el nombre de nuclis. A més, el planificador de Linux aplica una estratègia de temps compartit que no ofereix bones prestacions quan s'executen aplicacions de graf. Per maximitzar la utilització del sistema, aquesta tesi proposa executar múltiples aplicacions de grafs al mateix processador, assignant a cadascuna el nombre òptim de nuclis (i adaptant el nombre de fils creats) dinàmicament. Pel que fa a la computació al núvol, aquesta tesi aborda tres grans reptes: la complexa infraestructura d'aquests sistemes, les característiques de les seues aplicacions i l'impacte de la interferència entre màquines virtuals (MV). En primer lloc, aquesta tesi presenta la plataforma experimental desenvolupada amb els principals components d'un sistema al núvol. Després, es presenta un ampli estudi de caracterització sobre un conjunt d'aplicacions de latència crítica representatives per identificar els punts que els proveïdors de serveis al núvol han de tenir en compte per millorar el rendiment i la utilització dels recursos. Finalment, es fa una proposta que de manera dinàmica permet detectar i estimar la interferència entre MV. L'enfocament es basa en mètriques que es poden monitoritzar fàcilment al núvol públic, ja que les MV han de tractar-se com a "caixes negres". Tota la investigació descrita es duu a terme respectant les restriccions i complint els requisits per ser aplicable en entorns de producció al núvol públic. En resum, aquesta tesi aborda la contenció en els principals recursos compartits del sistema en el context de la consolidació de servidors. Els resultats experimentals mostren que s'obtenen importants guanys sobre Linux. En els processadors amb una LLC inclusiva, el temps d'execució (TT) es redueix en més d'un 40%, mentres que es millora l'IPC en més d'un 3%. En una LLC no inclusiva, l'equitat i el TT es milloren en un 44% i un 24%, respectivament, al mateix temps que s'obté una millora del rendiment de fins a un 3,5%. Distribuint els nuclis del processador de manera eficient es pot obtindre una equitat quasi perfecta (94%), i el TT pot reduir-se fins a un 80%. En entorns de computació al núvol, la degradació del rendiment pot estimar-se amb un error de predicció global d'un 5%. Totes les propostes presentades en aquesta tesi han sigut dissenyades per a ser aplicades en processadors de servidors comercials sense requerir cap informació prèvia, prenent decisions dinàmicament amb dades recollides dels comptadors de prestacions. / [EN] One of the main concerns of today's data centers is to maximize server utilization. In each server processor, multiple applications are executed concurrently, increasing resource efficiency. However, performance and fairness highly depend on the share of resources that each application receives, leading to performance unpredictability. The rising number of cores (and running applications) with every new generation of processors is leading to a growing concern for interference at the shared resources. This thesis focuses on addressing resource interference when different applications are consolidated on the same server processor from two main perspectives: high-performance computing (HPC) and cloud computing. In the context of HPC, resource management approaches are proposed to reduce inter-application interference at two major critical resources: the last level cache (LLC) and the processor cores. The LLC plays a key role in the system performance of current multi-cores by reducing the number of long-latency main memory accesses. LLC partitioning approaches are proposed for both inclusive and non-inclusive LLCs, as both designs are present in current server processors. In both cases, newly problematic LLC behaviors are identified and efficiently detected, granting a larger cache share to those applications that use best the LLC space. As for processor cores, many parallel applications, like graph applications, do not scale well with an increasing number of cores. Moreover, the default Linux time-sharing scheduler performs poorly when running graph applications, which process vast amounts of data. To maximize system utilization, this thesis proposes to co-locate multiple graph applications on the same server processor by assigning the optimal number of cores to each one, dynamically adapting the number of threads spawned by the running applications. When studying the impact of system-shared resources on cloud computing, this thesis addresses three major challenges: the complex infrastructure of cloud systems, the nature of cloud applications, and the impact of inter-VM interference. Firstly, this thesis presents the experimental platform developed to perform representative cloud studies with the main cloud system components (hardware and software). Secondly, an extensive characterization study is presented on a set of representative latency-critical workloads which must meet strict quality of service (QoS) requirements. The aim of the studies is to outline issues cloud providers should consider to improve performance and resource utilization. Finally, we propose an online approach that detects and accurately estimates inter-VM interference when co-locating multiple latency-critical VMs. The approach relies on metrics that can be easily monitored in the public cloud as VMs are handled as ``black boxes''. The research described above is carried out following the restrictions and requirements to be applicable to public cloud production systems. In summary, this thesis addresses contention in the main system shared resources in the context of server consolidation, both in HPC and cloud computing. Experimental results show that important gains are obtained over the Linux OS scheduler by reducing interference. In inclusive LLCs, turnaround time (TT) is reduced by over 40% while improving IPC by more than 3%. In non-inclusive LLCs, fairness and TT are improved by 44% and 24%, respectively, while improving performance by up to 3.5%. By distributing core resources efficiently, almost perfect fairness can be obtained (94%), and TT can be reduced by up to 80%. In cloud computing, performance degradation due to resource contention can be estimated with an overall prediction error of 5%. All the approaches proposed in this thesis have been designed to be applied in commercial server processors without requiring any prior information, making decisions dynamically with data collected from hardware performance counters. / Pons Escat, L. (2023). Interference Analysis and Resource Management in Server Processors: from HPC to Cloud Computing [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/195840

Στην παρούσα διδακτορική διατριβή προτείνονται τεχνικές για την βελτιστοποίηση της ποιότητας των παρεχομένων υπηρεσιών στους χρήστες σύγχρονων ασύρματων τηλεπικοινωνιακών συστημάτων που ως τεχνολογίες πρόσβασης έχουν την πολλαπλή πρόσβαση ορθογωνικής διαίρεσης συχνότητας και την πολλαπλή πρόσβαση διαίρεσης κώδικα. Οι τεχνικές που αναπτύχθηκαν αφορούν επαναληπτικούς αλγόριθμους κατανομής των διαθέσιμων ραδιοπόρων και εφαρμόζοναι κυρίως στην κατερχόμενη των ασύρματων συστημάτων. Ως παράμετροι της ποιότητας των παρεχόμενων υπηρεσιών θεωρούνται: το ελάχιστο απαιτούμενο επίπεδο ρυθμού μετάδοσης των δεδομέων, ο ρυθμός των λανθασμέων bit, και η ελάχιστη απαιτούμενη ποσότητα ραδιοπόρων σε κάθε χρήστη. Η αξιολόγηση των τεχνικών που προτείνονται γίνεται μέσω δεικτών της απόδοσής τους, οι οποίοι είναι: η πιθανότητα παραβίασης της ποιότητας της υπηρεσίας, ο δείκτης δικαιοσύνης του συστήματος, ο ρυθμός μετάδοσης δεδομένων στα άκρα της κυψέλης και η χωρητικότητα της κυψέλης. Για την εξαγωγή των δεικτών αυτών είναι απαραίτητα στατιστικά δεδομένα, τα οποία συλλέγονται μέσα από μεγάλο αριθμό προσομοιώσεων. / This doctoral thesis proposes QoS optimization techniques in modern wireless telecommunication systems, whereby orthogonal frequency division multiple access and code division are used. The proposed techniques are iterative resource allocation algorithms which are mainly suitable for the downlink of wireless networks. The minimum required level of data rate, the bit error rate and the minimum number of resources per user are considered as quality of service parameters. The validation of the proposed techniques is done through the performance of performance metrics like the : the quality of service violation probability, the system fairness index, the cell-edge data rate and the cell capacity. Statistical data are required which are collected through extensive simulation

La quinta generación de redes móviles (5G) se encuentra a la vuelta de la esquina. Se espera provea de beneficios extraordinarios a la población y que resuelva la mayoría de los problemas de las redes 4G actuales. El éxito de 5G, cuya primera fase de estandarización ha sido completada, depende de tres pilares: comunicaciones tipo-máquina masivas, banda ancha móvil mejorada y comunicaciones ultra fiables y de baja latencia (mMTC, eMBB y URLLC, respectivamente). En esta tesis nos enfocamos en el primer pilar de 5G, mMTC, pero también proveemos una solución para lograr eMBB en escenarios de distribución masiva de contenidos. Específicamente, las principales contribuciones son en las áreas de: 1) soporte eficiente de mMTC en redes celulares; 2) acceso aleatorio para el reporte de eventos en redes inalámbricas de sensores (WSNs); y 3) cooperación para la distribución masiva de contenidos en redes celulares. En el apartado de mMTC en redes celulares, esta tesis provee un análisis profundo del desempeño del procedimiento de acceso aleatorio, que es la forma mediante la cual los dispositivos móviles acceden a la red. Estos análisis fueron inicialmente llevados a cabo por simulaciones y, posteriormente, por medio de un modelo analítico. Ambos modelos fueron desarrollados específicamente para este propósito e incluyen uno de los esquemas de control de acceso más prometedores: access class barring (ACB). Nuestro modelo es uno de los más precisos que se pueden encontrar en la literatura y el único que incorpora el esquema de ACB. Los resultados obtenidos por medio de este modelo y por simulación son claros: los accesos altamente sincronizados que ocurren en aplicaciones de mMTC pueden causar congestión severa en el canal de acceso. Por otro lado, también son claros en que esta congestión se puede prevenir con una adecuada configuración del ACB. Sin embargo, los parámetros de configuración del ACB deben ser continuamente adaptados a la intensidad de accesos para poder obtener un desempeño óptimo. En la tesis se propone una solución práctica a este problema en la forma de un esquema de configuración automática para el ACB; lo llamamos ACBC. Los resultados muestran que nuestro esquema puede lograr un desempeño muy cercano al óptimo sin importar la intensidad de los accesos. Asimismo, puede ser directamente implementado en redes celulares para soportar el tráfico mMTC, ya que ha sido diseñado teniendo en cuenta los estándares del 3GPP. Además de los análisis descritos anteriormente para redes celulares, se realiza un análisis general para aplicaciones de contadores inteligentes. Es decir, estudiamos un escenario de mMTC desde la perspectiva de las WSNs. Específicamente, desarrollamos un modelo híbrido para el análisis de desempeño y la optimización de protocolos de WSNs de acceso aleatorio y basados en cluster. Los resultados muestran la utilidad de escuchar el medio inalámbrico para minimizar el número de transmisiones y también de modificar las probabilidades de transmisión después de una colisión. En lo que respecta a eMBB, nos enfocamos en un escenario de distribución masiva de contenidos, en el que un mismo contenido es enviado de forma simultánea a un gran número de usuarios móviles. Este escenario es problemático, ya que las estaciones base de la red celular no cuentan con mecanismos eficientes de multicast o broadcast. Por lo tanto, la solución que se adopta comúnmente es la de replicar e contenido para cada uno de los usuarios que lo soliciten; está claro que esto es altamente ineficiente. Para resolver este problema, proponemos el uso de esquemas de network coding y de arquitecturas cooperativas llamadas nubes móviles. En concreto, desarrollamos un protocolo para la distribución masiva de contenidos, junto con un modelo analítico para su optimización. Los resultados demuestran que el modelo propuesto es simple y preciso, y que el protocolo puede reducir el con / La cinquena generació de xarxes mòbils (5G) es troba molt a la vora. S'espera que proveïsca de beneficis extraordinaris a la població i que resolga la majoria dels problemes de les xarxes 4G actuals. L'èxit de 5G, per a la qual ja ha sigut completada la primera fase del qual d'estandardització, depén de tres pilars: comunicacions tipus-màquina massives, banda ampla mòbil millorada, i comunicacions ultra fiables i de baixa latència (mMTC, eMBB i URLLC, respectivament, per les seues sigles en anglés). En aquesta tesi ens enfoquem en el primer pilar de 5G, mMTC, però també proveïm una solució per a aconseguir eMBB en escenaris de distribució massiva de continguts. Específicament, les principals contribucions són en les àrees de: 1) suport eficient de mMTC en xarxes cel·lulars; 2) accés aleatori per al report d'esdeveniments en xarxes sense fils de sensors (WSNs); i 3) cooperació per a la distribució massiva de continguts en xarxes cel·lulars. En l'apartat de mMTC en xarxes cel·lulars, aquesta tesi realitza una anàlisi profunda de l'acompliment del procediment d'accés aleatori, que és la forma mitjançant la qual els dispositius mòbils accedeixen a la xarxa. Aquestes anàlisis van ser inicialment dutes per mitjà de simulacions i, posteriorment, per mitjà d'un model analític. Els models van ser desenvolupats específicament per a aquest propòsit i inclouen un dels esquemes de control d'accés més prometedors: el access class barring (ACB). El nostre model és un dels més precisos que es poden trobar i l'únic que incorpora l'esquema d'ACB. Els resultats obtinguts per mitjà d'aquest model i per simulació són clars: els accessos altament sincronitzats que ocorren en aplicacions de mMTC poden causar congestió severa en el canal d'accés. D'altra banda, també són clars en què aquesta congestió es pot previndre amb una adequada configuració de l'ACB. No obstant això, els paràmetres de configuració de l'ACB han de ser contínuament adaptats a la intensitat d'accessos per a poder obtindre unes prestacions òptimes. En la tesi es proposa una solució pràctica a aquest problema en la forma d'un esquema de configuració automàtica per a l'ACB; l'anomenem ACBC. Els resultats mostren que el nostre esquema pot aconseguir un acompliment molt proper a l'òptim sense importar la intensitat dels accessos. Així mateix, pot ser directament implementat en xarxes cel·lulars per a suportar el trànsit mMTC, ja que ha sigut dissenyat tenint en compte els estàndards del 3GPP. A més de les anàlisis descrites anteriorment per a xarxes cel·lulars, es realitza una anàlisi general per a aplicacions de comptadors intel·ligents. És a dir, estudiem un escenari de mMTC des de la perspectiva de les WSNs. Específicament, desenvolupem un model híbrid per a l'anàlisi de prestacions i l'optimització de protocols de WSNs d'accés aleatori i basats en clúster. Els resultats mostren la utilitat d'escoltar el mitjà sense fil per a minimitzar el nombre de transmissions i també de modificar les probabilitats de transmissió després d'una col·lisió. Pel que fa a eMBB, ens enfoquem en un escenari de distribució massiva de continguts, en el qual un mateix contingut és enviat de forma simultània a un gran nombre d'usuaris mòbils. Aquest escenari és problemàtic, ja que les estacions base de la xarxa cel·lular no compten amb mecanismes eficients de multicast o broadcast. Per tant, la solució que s'adopta comunament és la de replicar el contingut per a cadascun dels usuaris que ho sol·liciten; és clar que això és altament ineficient. Per a resoldre aquest problema, proposem l'ús d'esquemes de network coding i d'arquitectures cooperatives anomenades núvols mòbils. En concret, desenvolupem un protocol per a realitzar la distribució massiva de continguts de forma eficient, juntament amb un model analític per a la seua optimització. Els resultats demostren que el model proposat és simple i precís / The 5th generation (5G) of mobile networks is just around the corner. It is expected to bring extraordinary benefits to the population and to solve the majority of the problems of current 4th generation (4G) systems. The success of 5G, whose first phase of standardization has concluded, relies in three pillars that correspond to its main use cases: massive machine-type communication (mMTC), enhanced mobile broadband (eMBB), and ultra-reliable low latency communication (URLLC). This thesis mainly focuses on the first pillar of 5G: mMTC, but also provides a solution for the eMBB in massive content delivery scenarios. Specifically, its main contributions are in the areas of: 1) efficient support of mMTC in cellular networks; 2) random access (RA) event-reporting in wireless sensor networks (WSNs); and 3) cooperative massive content delivery in cellular networks. Regarding mMTC in cellular networks, this thesis provides a thorough performance analysis of the RA procedure (RAP), used by the mobile devices to switch from idle to connected mode. These analyses were first conducted by simulation and then by an analytical model; both of these were developed with this specific purpose and include one of the most promising access control schemes: the access class barring (ACB). To the best of our knowledge, this is one of the most accurate analytical models reported in the literature and the only one that incorporates the ACB scheme. Our results clearly show that the highly-synchronized accesses that occur in mMTC applications can lead to severe congestion. On the other hand, it is also clear that congestion can be prevented with an adequate configuration of the ACB scheme. However, the configuration parameters of the ACB scheme must be continuously adapted to the intensity of access attempts if an optimal performance is to be obtained. We developed a practical solution to this problem in the form of a scheme to automatically configure the ACB; we call it access class barring configuration (ACBC) scheme. The results show that our ACBC scheme leads to a near-optimal performance regardless of the intensity of access attempts. Furthermore, it can be directly implemented in 3rd Generation Partnership Project (3GPP) cellular systems to efficiently handle mMTC because it has been designed to comply with the 3GPP standards. In addition to the analyses described above for cellular networks, a general analysis for smart metering applications is performed. That is, we study an mMTC scenario from the perspective of event detection and reporting WSNs. Specifically, we provide a hybrid model for the performance analysis and optimization of cluster-based RA WSN protocols. Results showcase the utility of overhearing to minimize the number of packet transmissions, but also of the adaptation of transmission parameters after a collision occurs. Building on this, we are able to provide some guidelines that can drastically increase the performance of a wide range of RA protocols and systems in event reporting applications. Regarding eMBB, we focus on a massive content delivery scenario in which the exact same content is transmitted to a large number of mobile users simultaneously. Such a scenario may arise, for example, with video streaming services that offer a particularly popular content. This is a problematic scenario because cellular base stations have no efficient multicast or broadcast mechanisms. Hence, the traditional solution is to replicate the content for each requesting user, which is highly inefficient. To solve this problem, we propose the use of network coding (NC) schemes in combination with cooperative architectures named mobile clouds (MCs). Specifically, we develop a protocol for efficient massive content delivery, along with the analytical model for its optimization. Results show the proposed model is simple and accurate, and the protocol can lead to energy savings of up to 37 percent when compared to the traditional approach. / Leyva Mayorga, I. (2018). On reliable and energy efficient massive wireless communications: the road to 5G [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/115484 / TESIS