Academic literature on the topic 'Internet Servers, Response Time, Fairness, Threads'

Cloud computing provides access to various services such as servers, storage and applications to the customers' as and when required. The services on the cloud can be accessed with minimum efforts through any handheld devices that are connected to the Internet. In IaaS cloud, the services to the customers are provided in the form of two leases, AR and BE. Here, a running BE lease can be preempted upon arrival of an AR lease as BE has lower priority. However, frequent preemption of the BE lease causes an overhead to the system and leads to customer dissatisfaction. In this paper, we propose a fairness algorithm called TATA to provide fairness among the leases. We evaluate the proposed algorithm on various synthetic datasets and compare the results with an existing fairness algorithm. The results of simulation show that TATA produces better response time for both the leases than the existing algorithm.

The development of the internet of things has spawned new information concepts such as educational information sharing. Due to the openness of the internet of things, all kinds of mobile terminal devices can rely on the internet of things for data communication, information interaction, and resource sharing. Although the development of the internet of things has brought convenience to people’s lives, the internet of things is facing severe challenges in the fields of internal data sharing and cache sharing of educational information. The existing resource sharing systems do not fully consider the problems of privacy, shared data security, and data access control. This paper mainly studies the network integrated resource cache sharing system of the education information center based on internet of things. The data management system of the network education information center is developed on the basis of the school teaching management system and lifelong education public service platform, combined with the actual situation of student information. This paper combines the enrollment and information workflow of the student information management website, analyzes the problems existing in the current workflow, and then uses computer technology to standardize and transform the workflow, realize the information of the built-in resources in the data management, and solve the problems of data cache sharing and data statistics in the management of the education information center. The simulation results show that with the increase in the number of concurrent threads, the average response time of the edge cloud system deployed with two servers is smaller than that of the edge cloud system deployed with a single server, and the cloud system has good scalability.

“Error: no such entry.” “The thread specified does not exist.” These messages appeared every now and then in my cyberethnography – a study of Russian-Israeli queer immigrants and their online social spaces. Anthropological research in cyberspace invites us to rethink the notion of “the field” and the very practice of ethnographic observation. In negotiating my own position as an anthropologist of online sociality, I was particularly inspired by Radhika Gajjala’s notion of “cyberethnography” as an epistemological and methodological practice of examining the relations between self and other, voice and voicelessness, belonging, exclusion, and silencing as they are mediated through information-communication technologies (“Interrupted” 183). The main cyberethnographic site of my research was the queer immigrants’ Website with its news, essays, and photo galleries, as well as the vibrant discussions that took place on the Website’s bulletin board. “The Forum,” as it was known among the participants, was visited daily by dozens, among them newbies, passers-by, and regulars. My study, dedicated to questions of home-making, violence, and belonging, was following the publications that appeared on the Website, as well as the daily discussions on the Forum. Both the publications and the discussions were archived since the Website’s creation in 2001 and throughout my fieldwork that took place in 2003-04. My participant observations of the discussions “in real time” were complemented by archival research, where one would expect to discover an anthropologist’s wildest dreams: the fully-documented everyday life of a community, a word-by-word account of what was said, when, and to whom. Or so I hoped. The “error” messages that appeared when I clicked on some of the links in the archive, or the absence of a thread I knew was there before, raised the question of erasure and deletion, of empty spaces that marked that which used to be, but which had ceased to exist. The “error” messages, in other words, disrupted my cyberethnography through what can be best described as haunting. “Haunting,” writes Avery Gordon in her Ghostly Matters, “describes how that which appears to be not there is often a seething presence, acting on and often meddling with taken-for-granted realities” (8). This essay looks into the seething presence of erasures in online archives. What is the role, I will ask, of online archives in the life of a cybercommunity? How and when are the archives preserved, and by whom? What are the relations between archives, erasure, and home-making in cyberspace? *** Many online communities based on mailing lists, newsgroups, or bulletin boards keep archives of their discussions – archives that at times go on for years. Sometimes they are accessible only to members of lists or communities that created them; other times they are open to all. Archived discussions can act as a form of collective history and as marks of belonging (or exclusion). As the records of everyday conversations remain on the Web, they provide a unique glance into the life of an online collective for a visitor or a newcomer. For those who participated in the discussions browsing through archives can bring nostalgic feelings: memories – pleasurable and/or painful – of times shared with others; memories of themselves in the past. Turning to archived discussions was not an infrequent act in the cybercommunity I studied. While there is no way to establish how many participants looked into how many archives, and how often they did so, there is a clear indicator that the archives were visited and reflected on. For one, old threads were sometimes “revived”: technically, a discussion thread is never closed unless the administrator decides to “freeze” it. If the thread is not “frozen,” anyone can go to an old discussion and post there; a new posting would automatically move an archived thread to the list of “recent”/“currently active” ones. As all the postings have times and dates, the reappearance of threads from months ago among the “recent discussions” indicates the use of archives. In addition to such “revivals,” every now and then someone would open a new discussion thread, posting a link to an old discussion and expressing thoughts about it. Sometimes it was a reflection on the Forum itself, or on the changes that took place there; many veteran participants wrote about the archived discussion in a sentimental fashion, remembering “the old days.” Other times it was a reflection on a participant’s life trajectory: looking at one’s old postings, a person would reflect on how s/he changed and sometimes on how the Website and its bulletin board changed his/her life. Looking at old discussions can be seen as performances of belonging: the repetitive reference to the archives constitutes the Forum as home with a multilayered past one can dwell on. Turning to the archives emphasises the importance of preservation, of keeping cyberwords as an object of collective possession and affective attachment. It links the individual and the collective: looking at old threads one can reflect on “how I used to be” and “how the Forum used to be.” Visiting the archives, then, constitutes the Website as simultaneously a site where belonging is performed, and an object of possession that can belong to a collective (Fortier). But the archives preserved on the Forum were never a complete documentation of the discussions. Many postings were edited immediately after appearance or later. In the first two and a half years of the Website’s existence any registered participant, as long as his/her nickname was not banned from the Forum, could browse through his/her messages and edit them. One day in 2003 one person decided to “commit virtual suicide” (as he and others called it). He went through all the postings and, since there was no option for deleting them all at once, he manually erased them one by one. Many participants were shocked to discover his acts, mourning him as well as the archives he damaged. The threads in which he had once taken part still carried signs of his presence: when participants edit their postings, all they can do is delete the text, leaving an empty space in the thread’s framework (only the administrator can modify the framework of a thread and delete text boxes). But the text box with name and date of each posting is still there. “The old discussions don’t make sense now,” a forum participant lamented, “because parts of the arguments are missing.” Following this “suicide” the Website’s administrator decided that from that point on participants could only edit their last posting but could not make any retrospective changes to the archives. Both the participants’ mourning of the mutilated threads and administrator’s decision suggest that there is a desire to preserve the archives as collective possession belonging to all and not to be tampered with by individuals. But the many conflicts between the administrator and some participants on what could be posted and what should be censored reveal that another form of ownership/ possession was at stake. “The Website is private property and I can do anything I like,” the administrator often wrote in response to those who questioned his erasure of other people’s postings, or his own rude and aggressive behaviour towards participants. Thus he broke the very rules of netiquette he had established – the Website’s terms of use prohibit personal attacks and aggressive language. Possession-as-belonging here was figured as simultaneously subjected to a collective “code of practice” and as arbitrary, dependant on one person’s changes of mind. Those who were particularly active in challenging the administrator (for example, by stating that although the Website is indeed privately owned, the interactions on the Forum belong to all; or by pointing out to the administrator that he was contradicting his own rules) were banned from the site or threatened with exclusion, and the threads where the banning was announced were sometimes deleted. Following the Forum’s rules, the administrator was censoring messages of an offensive nature, for example, commercial advertisements or links to pornographic Websites, as well as some personal attacks between participants. But among the threads doomed for erasure were also postings of a political nature, in particular those expressing radical left-wing views and opposing the tone of political loyalty dominating the site (while attacks on those participants who expressed the radical views were tolerated and even encouraged by the administrator). *** The archives that remain on the site, then, are not a full documentation of everyday narratives and conversations but the result of selection and regulation of both individual participants and – predominantly – the administrator. These archives are caught between several contradictory approaches to the Forum. One is embedded within the capitalist notion of payment as conferring ownership: I paid for the domain, says the administrator, therefore I own everything that takes place there. Another, manifested in the possibility of editing one’s postings, views cyberspeech as belonging first and foremost to the speaker who can modify and erase them as s/he pleases. The third defines the discussions that take place on the Forum as collective property that cannot be ruled by a single individual, precisely because it is the result of collective interaction. But while the second and the third approaches are shared by most participants, it is the idea of private ownership that seemed to dominate and facilitate most of the erasures. Erasure and modification performed by the administrator were not limited to censorship of particular topics, postings, or threads. The archive of the Forum as a whole was occasionally “cleared.” According to the administrator, the limited space on the site required “clearance” of the oldest threads to make room for new ones. Decisions about such clearances were not shared with anyone, nor were the participants notified about it in advance. One day parts of the archive simply disappeared, as I discovered during my fieldwork. When I began daily observations on the Website in December 2003, I looked at the archives page and saw that the General Forum section of the Forum went back for about a year and a half, and the Lesbian Forum section for about a year. I then decided to follow the discussions as they emerged and unfolded for 5-6 months, saving only the most interesting threads in my field diary, and to download all the archived threads later, for future detailed analysis. But to my great surprise, in May 2004 I discovered that while the General Forum still dated back to September 2002, the oldest thread on the Lesbian Forum was dated December 2003! All earlier threads were removed without any notice to Forum participants; and, as I learned later, no record of the threads was kept on- or offline. These examples of erasure and “clearance” demonstrate the complexity of ownership on the site: a mixture of legal and capitalist power intertwined with social hierarchies that determine which discussions and whose words are (more) valuable (The administrator has noted repeatedly that the discussions on the Lesbian Forum are “just chatter.” Ironically, both the differences in style between the General Forum and the Lesbian Forum and the administrator’s account of them resemble the (stereo)typical heterosexual gendering of talk). And while the effects and the results of erasure are compound, they undoubtly point to the complexity – and fragility! – of “home” in cyberspace and to the constant presence of violence in its constitution. During my fieldwork I felt the strange disparity between the narratives of the Website as a homey space (expressed both in the site’s official description and in some participants’ account of their experiences), and the frequent acts of erasure – not only of particular participants but more broadly of large parts of its archives. All too often, the neat picture of the “community archive” where one can nostalgically dwell on the collective past was disrupted by the “error” message. Error: no such entry. The thread specified does not exist. It was not only the incompleteness of archives that indicated fights and erasures. As I gradually learned throughout my fieldwork, the history of the Website itself was based on internal conflicts, omitted contributions, and constantly modified stories of origins. For example, the story of the Website’s establishment, as it was published in the About Us section of the site and reprinted in celebratory texts of the first anniversaries, presents the site as created by “three fathers.” The three were F, the administrator, M. who wrote, edited, and translated most of the material, and the third person whose name was never mentioned. When I asked about him on the site and later in interviews with both M. and F., they repeatedly and steadily ignored the question, and changed the subject of conversation. But the third “father” was not the only one whose name was omitted. In fact, the original Website was created by three women and another man. M. and F. joined later, and soon afterwards F., who had acted as the administrator during my fieldwork, took over the material and moved the site to another domain. Not only were the original creators erased from the site’s history; they were gradually ostracised from the new Website. When I interviewed two of the women, I mentioned the narrative of the site as a “child of three fathers.” “More like an adopted child,” chuckled one of them with bitterness, and told me the story of the original Website. Moved by their memories, the two took me to the computer. They went to the Internet Archive’s “WayBack Machine” Website – a mega-archive of sorts, an online server that keeps traces of old Web pages. One of the women managed to recover several pages of the old Website; sad and nostalgic, she shared with me the few precious traces of what was once her and her friends’ creation. But those, too, were haunted pages – most of the hyperlinks there generated “error” messages instead of actual articles or discussion threads. Error: no such entry. The thread specified does not exist. After a few years of working closely together on their “child,” M. and F. drifted apart, too. The hostility between the two intensified. Old materials (mostly written, translated, or edited by M. over a 3 year period) were moved into an archive by F. the administrator. They were made accessible through a small link hidden at the bottom of the homepage. One day they disappeared completely. Shortly afterwards, in September 2006, the Website celebrated its fifth anniversary. For this occasion the administrator wrote “the history of the Website,” where he presented it as his enterprise, noting in passing two other contributors whose involvement was short and marginal. Their names were not mentioned, but the two were described in a defaming and scornful way. *** So where do the “error” messages take us? What do they tell us about homes and communities in cyberspace? In her elaboration on cybercommunities, Radhika Gajjala notes that: Cyberspace provides a very apt site for the production of shifting yet fetishised frozen homes (shifting as more and more people get online and participate, frozen as their narratives remain on Websites and list archives through time in a timeless floating fashion) (“Interrupted”, 178). Gajjala’s notion of shifting yet fetishised and frozen homes is a useful term for capturing the nature of communication on the Forum throughout the 5 years of its existence. It was indeed a shifting home: many people came and participated, leaving parts of themselves in the archives; others were expelled and banned, leaving empty spaces and traces of erasure in the form of “error” messages. The presence of those erased or “cleared” was no longer registered in words – an ultimate sign of existence in the text-based online communication. And yet, they were there as ghosts, living through the traces left behind and the “seething presence” of haunting (Gordon 8). The Forum was a fetishised home, too, as the negotiation of ownership and the use of old threads demonstrate. However, Gajjala’s vision of archives suggests their wholeness, as if every word and every discussion is “frozen” in its entirety. The idea of fetishised homes does gesture to the complex and complicated reading of the archives; but what is left unproblematic are the archives themselves. Being attentive to the troubled, incomplete, and haunted archives invites a more careful and critical reading of cyberhomes – as Gajjala herself demonstrates in her discussion of online silences – and of the interrelation of violence and belonging in it (CyberSelves 2, 5). Constituted in cyberspace, the archives are embedded in the particular nature of online sociality, with its fantasy of timeless and floating traces, as well as with its brutality of deletion. Cyberwords do remain on archives and servers, sometimes for years; they can become ghosts of people who died or of collectives that no longer exist. But these ghosts, in turn, are haunted by the words and Webpages that never made it into the archives – words that were said but then deleted. And of course, cyberwords as fetishised and frozen homes are also haunted by what was never said in the first place, by silences that are as constitutive of homes as the words. References Fortier, Anne-Marie. “Community, Belonging and Intimate Ethnicity.” Modern Italy 1.1 (2006): 63-77. Gajjala, Radhika. “An Interrupted Postcolonial/Feminist Cyberethnography: Complicity and Resistance in the ‘Cyberfield’.” Feminist Media Studies 2.2 (2002): 177-193. Gajjala, Radhika. Cyber Selves: Feminist Ethnographies of South-Asian Women. Oxford: Alta Mira Press, 2004. Gordon, Avery. Ghostly Matters: Haunting and the Sociological Imagination. Minneapolis and London: U of Minneapolis P, 1997. Citation reference for this article MLA Style Kuntsman, Adi. "“Error: No Such Entry”: Haunted Ethnographies of Online Archives." M/C Journal 10.5 (2007). echo date('d M. Y'); ?> <http://journal.media-culture.org.au/0711/05-kuntsman.php>. APA Style Kuntsman, A. (Oct. 2007) "“Error: No Such Entry”: Haunted Ethnographies of Online Archives," M/C Journal, 10(5). Retrieved echo date('d M. Y'); ?> from <http://journal.media-culture.org.au/0711/05-kuntsman.php>.

This thesis presents a new approach to ensuring fair service for highly concurrent requests. Our design uses the advantages of staged event-driven architecture (SEDA) to support high-concurrent loadings and makes use of control theory to manage the system performance. In order to guarantee the quality of service is fairly made to each request, based on SEDA, the control system for fairness is developed as a combination of a global control framework and a set of local self-tune stags. The global control framework is used to control the performance of the whole staged network at the top-level, aimed at coordinating the performance of the stages in the network. On the other hand, each self-tune stage under the control framework is built on the thread pool model, and will use automatic control theory to adjust its performance locally in order to meet the overall target performance. The automatic control system in each stage consists of an automatic modeling mechanism and a feedback module, which optimizes the controller parameters in the system automatically and guarantees the quality of performance (service rate here) for the stage at runtime. Based on mathematical proof and simulation results, our designs are implemented in a SEDA-based web server running in a dynamic loading environment. Results demonstrate that the performance of the new system in the real world is almost the same as the theoretical results. It demonstrates that the design is able to adaptively ensure the quality of service to the high-concurrent requests fairly. Compared to the original SEDA design, our design is an effective and handy approach to significantly enhancing the performance of SEDA in a variety of aspects, including fairer service, faster convergent speed, better robustness, higher accuracy and ease of deployment in various practical applications.

Master of Engineering (Research)
This thesis presents a new approach to ensuring fair service for highly concurrent requests. Our design uses the advantages of staged event-driven architecture (SEDA) to support high-concurrent loadings and makes use of control theory to manage the system performance. In order to guarantee the quality of service is fairly made to each request, based on SEDA, the control system for fairness is developed as a combination of a global control framework and a set of local self-tune stags. The global control framework is used to control the performance of the whole staged network at the top-level, aimed at coordinating the performance of the stages in the network. On the other hand, each self-tune stage under the control framework is built on the thread pool model, and will use automatic control theory to adjust its performance locally in order to meet the overall target performance. The automatic control system in each stage consists of an automatic modeling mechanism and a feedback module, which optimizes the controller parameters in the system automatically and guarantees the quality of performance (service rate here) for the stage at runtime. Based on mathematical proof and simulation results, our designs are implemented in a SEDA-based web server running in a dynamic loading environment. Results demonstrate that the performance of the new system in the real world is almost the same as the theoretical results. It demonstrates that the design is able to adaptively ensure the quality of service to the high-concurrent requests fairly. Compared to the original SEDA design, our design is an effective and handy approach to significantly enhancing the performance of SEDA in a variety of aspects, including fairer service, faster convergent speed, better robustness, higher accuracy and ease of deployment in various practical applications.