PQEMU移植到x86架構上後，所面臨的問題。主要影響問題有兩個，一個是關於開啟太多執行緒所造成時常切換的負載問題、另一個是在模擬太多顆CPU時，牆上時鐘的一分鐘依然是一分鐘，但是對於模擬器而言，卻用少數實體CPU去模擬到255顆虛擬CPU，這樣造成時間上的誤差。對於此問題，可以假設時間中斷處理每十毫秒發送一個，處理時間需要花一百微秒，十毫秒除一百微秒結果為一百，我們可以得知，如果我們只有一個實體CPU，超過模擬一百個CPU時，超過此個數的虛擬CPU都要等到下個時間中斷處理才可以處理，這樣就產生了時間中短累積的現象，對於模擬器來說，這是個極限，可以去擴大這時間減少累積問題。我們使用排程方法去減輕CPU時常切換的負載問題，然後遮罩時間中斷去擴大時間中斷裝置發送時間中斷間隔。

Scheduling and timer interrupt extends PQEMU SCC to execute and supports to emulate 255 VCPUs on x86 platform. This paper strongly emphasizes while we emu-late 255 VCPUs, what problems we face. These problems lead to operating system lite then slow heavy then crash. Therefore, we can know the significance of these problem, these problems are caused by context switching, host scheduler and timing problem. Nonetheless, this paper provides two methods of solving these problems which are group scheduling and mask timer interrupt, group scheduling want to solve the prob-lem which is the overhead of context switch or host scheduler. Moreover, we want to decrease mask timer interrupt to solve the problem which is accumulative timer inter-rupts because time interval of tick is fix but we emulate number of VCPUs larger than physical CPU so that we have small time slice to execute every VCPU, we enlarge time interval of tick by using mask timer interrupt. Above all, we implement group scheduling and mask timer interrupt so that we can emulate 255 VCPUs, despite of emulating 255 VCPUs, it just need few minute to start up.

[1]Jiun-Hung Ding; Po-Chun Chang; Wei-Chung Hsu; Yeh-Ching Chung; , "PQEMU: A Parallel System Simulator Based on QEMU," Parallel and Distrib-uted Systems (ICPADS), 2011 IEEE 17th International Conference on , vol., no., pp.276-283, 7-9 Dec. 2011 doi: 10.1109/ICPADS.2011.102
[2] MARSSx86: A Full System Simulator for Mulitcore x86 CPUs
Avadh Patel, Furat Afram, Shunfei Chen, Kanad Ghose (SUNY Binghamton)
[3]PTLsim: A Cycle Accurate Full System x86-64 Microarchitectural Simulator. In Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2007 (San Jose, CA, 2007). 23-34.
[4]COREMU: a scalable and portable parallel full-system simulator by: Zhaoguo Wang, Ran Liu, Yufei Chen, Xi Wu, Haibo Chen, Weihua Zhang, Binyu Zang In Proceedings of the 16th ACM symposium on Principles and practice of parallel programming (2011), pp. 213-222, doi:10.1145/1941553.1941583
[5]VMware. Timekeeping in VMware Virtual Machines, May 2010. http://www.vmware.com/vmtn/resources/238.
[6]Gengbin Zheng, Laxmikant V. Kale, Orion Sky Lawlor, "Multiple Flows of Control in Migratable Parallel Programs," icppw,2006 International Conference on Parallel Processing Workshops (ICPPW'06), 2006
[7]Pthreads for Dynamic Parallelism. Girija J. Narlikar and Guy E. BlellochProceedings of Supercomputing 98: High Performance Networking and Computing, November 1998
[8] Ye Dun-fan, Zhou Fei-fan, Min Liang-liang. "Design and Implementation of High-Precision Timer in Linux". CSIE '09 Proceedings of the 2009 WRI World Congress on Computer Science and Information Engineering