Network arrivals are often modeled as Poisson processes for analytic simplicity, even though a number of traffic studies have shown that packet interarrivals are not exponentially distributed. We evaluate 24 wide-area traces, investigating a number of wide-area TCP arrival processes (session and connection arrivals, FTP data connection arrivals within FTP sessions, and TELNET packet arrivals) to determine the error introduced by modeling them using Poisson processes. We find that user-initiated TCP session arrivals, such as remotelogin and file-transfer, are well-modeled as Poisson processes with fixed hourly rates, but that other connection arrivals deviate considerably from Poisson; that modeling TELNET packet interarrivals as exponential grievously underestimates the burstiness of TELNET traffic, but using the empirical Tcplib [Danzig et al, 1992] interarrivals preserves burstiness over many time scales; and that FTP data connection arrivals within FTP sessions come bunched into “connection bursts,” the largest of which are so large that they completely dominate FTP data traffic. Finally, we offer some results regarding how our findings relate to the possible self-similarity of widearea traffic.

Abstract not found

We describe our experiences with the implementation of a process migration mechanism for the distributed operating system Amoeba. After describing our design goals, we present our implementation for Amoeba. Though our goals have very largely been met, we have fallen short of the goal of complete transparency, and we discuss the consequences of that. We also present performance figures, indicating that the speed of process migration is limited only by the throughput of the network adapters used in our configuration, and that the overhead is comparable to that of process creation. We conclude with a review of the degree to which our design goals have been met, and discussion of the lessons learnt.

The paper investigates the area of dynamic load balancing with the specific target of massively parallel architectures. The lack of centralisation makes the architectures cost effective and scalable but requires suitable simple system policies without centralisation and with decisions based on a limited amount of information. The paper analyses the class of load balancing policies inspired to diffusion and shows how they can lead a system to a load balanced configuration. The paper evaluates and compares the effectiveness of several diffusion-based policies depending both on the external environment (i.e., the properties of the system load) and on the internal parameters. All presented policies show a robust and scalable behaviour: they are able to reach a good load balancing quality with promptness, low intrusion and little dependence on the system size. Moreover, the paper shows that the enlargement of the scope of one diffusive policy can be effective only in case of slow load dynam...

ions : : : : : : : : : : : : : : : : : : : : : : : : 53 5.2 Supervisor Interface : : : : : : : : : : : : : : : : : : : : : : : : : : : : 58 5.3 mmuContext Operations : : : : : : : : : : : : : : : : : : : : : : : : : 60 5.4 mmuPage Operations : : : : : : : : : : : : : : : : : : : : : : : : : : : 60 5.5 Network Device Manager Interface : : : : : : : : : : : : : : : : : : : 62 5.6 Deqna Operations : : : : : : : : : : : : : : : : : : : : : : : : : : : : 62 5.7 Segment Mapper Operations : : : : : : : : : : : : : : : : : : : : : : 64 6.1 Chorus Kernel Module Interface : : : : : : : : : : : : : : : : : : : : : 68 6.2 Potentially Blocking Chorus System Calls : : : : : : : : : : : : : : : 69 6.3 Actor State Information : : : : : : : : : : : : : : : : : : : : : : : : : 72 6.4 Region State Information : : : : : : : : : : : : : : : : : : : : : : : : : 74 6.5 Thread State Information : : : : : : : : : : : : : : : : : : : : : : : : 76 6.6 Port State Information : : : : : : : : : : : : : : : : : : : ...

A sliding strategy for load balancing is introduced. The strategy groups a certain number of adjacent nodes to perform a load balancing process. Upon the completion of a given period, the groups are to be rotated by shifting each group one position to the right, thus produces different groups. This strategy (sort of clustering) not only reduces the load balancing overheads, but also it could be utilized as a backbone by any load balancing strategy. The proposed load balancing strategy always converges, and tends to be in a steady state in a negligible processing time. In this paper, the load status and the locations of the nodes regarding the system’s topology are irrelevant to load balancing process. The new algorithm can be always applied to any distributed system, even if it is heavily loaded, since the cost of scheduling is very low due to the highly reduced number of messages. This is achieved by reducing dramatically the overheads incurred from attached information tables, message passing, job thrashing, and response time.

Abstract—Developing CPU scheduling algorithms and understanding their impact in practice can be difficult and time consuming due to the need to modify and testoperating systemkernel code and measure the resulting performance on a consistent workload of real applications. To address this problem, we have developed WARP, a trace-driven virtualized scheduler execution environment that can dramatically simplify and speed the development of CPU schedulers. WARP is easy to use as it can run unmodified kernel scheduling code and can be used with standard user-space debugging and performance monitoring tools. It accomplishes this by virtualizing operating system and hardware events to decouple kernel scheduling code from its native operating system and hardware environment. A simple kernel tracing toolkit can be used with WARP to capture traces of all CPU scheduling related events from a real system. WARP can then replay these traces in its virtualized environment with the same timing characteristics as in the real system. Traces can be used with different schedulers to provide accurate comparisons of scheduling performance for a given application workload. We have implemented a WARP Linux prototype. Our results show that WARP can use application traces captured from its toolkit to accurately reflect the scheduling behavior of the real Linux operating system. Furthermore, testing scheduler behavior using WARP with application traces can be two orders of magnitude faster than running the applications using Linux. I.