**1. Introduction**

28 Will-be-set-by-IN-TECH

222 Emerging Informatics – Innovative Concepts and Applications

OASIS consortium (2004). Ws-security core specification 1.1. http://www.oasis- open.org/

URL: *http://www.owasp.org/index.php/Category:OWASP\_Testing \_Project#OWASP\_*

validating safety properties of reactive systems, *in* J. Fitzgerald, A. Tarlecki & I. Hayes

*2010 Fifth International Conference on Internet and Web Applications and Services*, IEEE

J. Bowen & M. Harman (eds), *Formal Methods and Testing*, Vol. 4949 of *Lecture Notes in Computer Science*, Springer Berlin / Heidelberg, Berlin, Heidelberg, chapter 1,

Rusu, V., Marchand, H. & Jéron, T. (2005). Automatic verification and conformance testing for

Salva, S. & Rabhi, I. (2010). Stateful web service robustness, *ICIW '10: Proceedings of the*

Senn, D., Basin, D. A. & Caronni, G. (2005). Firewall conformance testing, *Testing of Communicating Systems (TestCom)*, Vol. 3502, LNCS, Springer, pp. 226–241. Singh, M. & Pattterh, S. (2010). Formal specification of common criteria based access control

Specification, O. U. (2002). Universal description, discovery and integration. http://www.

Tidwell, D. (2000). Web services, the web's next revolution, *IBM developer Works*, IBM books. Tretmans, J. (2008). Model Based Testing with Labelled Transition Systems, *in* R. Hierons,

WS-I organization (2006). Basic profile. URL: *http://www.ws-i.org/docs/charters/WSBasic\_ Profile*

OASIS standards organization (2009). Xacml (extensible access control markup language).

committees/tc\_home.php?wg\_abbrev=wss.

(eds), *Formal Methods 2005 (FM05)*, LNCS, Springer.

Computer Society, Washington, DC, USA, pp. 167–173.

policy, *International Journal of Network Security*, pp. 139–148.

pp. 1–38. URL: *http://dx.doi.org/10.1007/978-3-540-78917-8\_1* World Wide Web Consortium (2001). Web services description language (wsdl). World Wide Web consortium (2003). Simple object access protocol v1.2 (soap).

URL: *http://xml.coverpages.org/xacml.html*

OWASP (2003). Owasp testing guide v3.0 project.

oasisopen.org /cover/uddi.html.

*\_ Charter2-1.pdf, (accessed May 1, 2010)*

*Testing\_Guide\_v3*

Emerging rich interactive Web services require timeliness and high availability. These applications are usually characterized as high I/O intensive service model such as ecommerce services, medical sciences including healthcare and digital imaging. [1,3]. These applications require continuous operation, non-stop service system and timeliness to achieve high assurance to meet Service Level Agreement (SLA). SLA is the explicit requirement of the Quality of Service (QoS), such as reliability and timeliness. SLA requirement in the emerging applications on the Internet needs Autonomous Decentralized System (ADS) [8] characteristics [2,4].

The usage of Web services on the Internet is increasing exponentially and giving rise to very large online community. Web service community behavior shows power functions (from 2.1 to 4) that is called "small world". Therefore, some web sites are much more popular and hence highly I/O intensive. In these websites, there is considerable response time delay due to increasing demand of user push type I/O request and its data coherence. Faded Information Field (FIF) technology supports pull type of read event access enhancement while Autonomous Decentralized System by different class of nodes by its service level. But Web services require interoperable communication for user push type also. Traditional system does not meet the dynamic demand and it doesn't have Multi layer-cache concept. To enhance the user push type I/O performance, there are two approaches. One is the cache node approach and the other is selecting a high performance device. Each of them has pros & cons. High speed device such as NAND Flash SSD has less capacity and very limited write life cycle time. Proxy cache node effects for read event but it doesn't achieve write event on each node dynamically. Thus the interoperable I/O performance is not enhanced by existing approaches. How to solve these issues by the system architecture is proposed by this paper. First is to achieve timeliness user pushing type I/O performance by using write back cache processing node (P-Node). Second is to maintain online property by trio nodes by dual data field configuration. The third is data availability which is achieved by dividing processing node and content node in two data fields and duplicating data storage partitions. This system architecture has two data fields with trio nodes Autonomous Decentralized

Autonomous Decentralized Multi-Layer

creation process is required initially.

Content Data Field.

Node storage partitions.

duplicate storage partitions.

Fig. 2. Initialization process

Initialization process is shown in Figure-2. 1. C-Node broadcasts its own node status.

5. C-Node notices P-Node for P-Node trio group creation. 6. P-Node is created by nearest P-Node autonomously.

7. Write event performed by L3 cache on P-Node.

Nodes.

**2.2 Initialization** 

space.

Cache System to Low Latency User Push Web Services 225

6. To achieve the timeliness I/O, the dedicated block cache is implemented on both

The storage space for all data is at C-node trio group. Each C-Node is connected three of them. To execute C-Node application program, P-Node is always required. Therefore, group

2. When other C-Node receives their node status, reply to it with own node status via

7. Once P-Node trio group and C-Node trio group is created, P-Node starts to mount C-

8. Here, P-Node has two mounting points on C-Node. P-Node mounts one storage partition via L3 cache space and another storage partition is mounted via non L3 cache

9. P-Node manages two storage partitions now. The data availability is achieved by the

3. Created Trio C-Node group, broadcasts the request of P-Node availability via C-DF. 4. Receive the initialization request from C-Node, P-node reply their node status.

8. Data availability achieved by duplicated storage partitions on each C-Node.

Multi Layer cache system. Processing node (P-Node) has L3 cache and it performs low latency of time response. L3 cache is dedicated block cache memory on P-Node. Because operating system managed memory doesn't hold specific block data of application services inside of the memory [10, 11], there have been a number of efforts to improve I/O performance however these are substantially different from our work. In [12], the author proposes Unified Buffer Cache (UBC). The focus is to unify the file system and virtual memory caches of file data to improve I/O transactions. However it is an unmanaged one level cache that is very much different from the L3 cache. Similarly [13], [14] provide solution for high I/O, based on RAM disk memory [18] and solid-state disk, and is altogether different from L3 block cache [16]. Other side of block cache is L4 cache. It is inside block device in the Content Node (C-Node). Pre-fetching read is performed by C-Node L4 cache. Thus, two different cache nodes manage user pushing type services model with low latency time web service.

Section 1 is introduction and section 2 is Autonomous multi-layer cache system architecture. Section 3 is its evaluation and section 4 concludes our work.
