基于虚拟机自省的运行时内存泄漏检测模型

doi:10.3969/j.issn.1000-436x.2013.z1.004

摘要/Abstract

摘要：

云计算及数据中心领域中已广泛采用虚拟化技术来尽可能消除虚拟计算环境中的内存泄漏是提高其可靠性的一种重要途径。提出了一种基于虚拟机自省机制的运行时内存泄漏的信息流检测模型与内存泄漏的判定方法，设计并实现了该模型的原型系统。通过对原型系统的有效性与性能评估实验分析，结果表明，该模型方法能有效地检测出运行时内存泄漏，并且具有较好的性能。

关键词: 虚拟机, 自省, 内存泄漏, 有效性, 性能

Abstract:

Virtualization technology has been widely used in the field of cloud computing and data center, and it is an important way to improve reliability of system under the virtual computing environment using runtime memory leak de-tecting to eliminate memory leaks. A model of runtime memory leak detection based on the virtual machine introspection and an approach to predication on memory leak were proposed. The prototype system of the model was designed and im-plemented. By analyzing and evaluating effectiveness and performance of the prototype system, the results show that these models and methods can effectively detect memory leaks, and have better performance.

Key words: virtual machine, introspection, memory leak, effectiveness, performance

肖如良,姜军,倪友聪,杜欣,谢国庆,蔡声镇. 基于虚拟机自省的运行时内存泄漏检测模型[J]. 通信学报, 2013, 34(Z1): 21-30.

Ru-liang XIAO,Jun JIANG,You-cong NI,Xin DU,Guo-qing XIE,Sheng-zhen CAI. Model of runtime memory leak detection based on the virtual machine introspection[J]. Journal on Communications, 2013, 34(Z1): 21-30.

图/表 9

图1

图2

图3

图4

图5

图6

表1

表2

表3

参考文献 10

[1]	PURIFY R . Purify: fast detection of memory leaks and access er-rors[EB/OL]. , 2012.
[2]	QIN F , LU S , ZHOU Y Y . SafeMem: exploiting ECC memory for detecting memory leaks and memory corruption during production runs[A]. Pro-ceedings of the HPCA[C]. San Francisco, USA, 2005.291-302.
[3]	BUNGALE P P , LUKC K . PinOS: a programmable framework for whole system dynamic instrumentation[A]. Proceedings of the ACM Conference on Virtual Execution Environments[C]. San Diego, California, USA, 2010.137-147.
[4]	汪小林，王振林，孙逸峰等．利用虚拟化平台进行内存泄露探测[J]．计算机学报， 2010,33(3):463-472. WANG X L , WANG Z L , SUN Y F , et al. Detecting memory leak via VMM[J]. Chinese Journal of Computers, 2010,33(3):463-472.
[5]	项国富，金海，邹德清等．基于虚拟化的安全监控[J]．软件学报， 2012,23(8):2173-2187. XIANG G F , JIN H , ZOU D Q , et al. Virtualization-based security monitoring[J]. Journal of Software, 2012,23(8):2173-2187.
[6]	王丽娜，高汉军，刘炜等．利用虚拟机监视器检测及管理隐藏进程[J]．计算机研究与发展， 2011,48(8):1534-1541. WANG L N , GAO H J , LIU W , et al. Detecting and managing hid-den process via hypervisor[J]. Journal of Computer Research and Development, 2011,48(8):1534-1541.
[7]	SHARIF M , LEE W , CUI W , et al. Secure in-VM monitoring using hardware virtualization[A]. Proc of the 16th ACM Conf on Computer and Communications Security[C]. New York, USA, 2009.477-487.
[8]	GARFINKEL T , ROSENBLUM M . A virtual machine introspection based architecture for intrusion detection[A]. Proc of the 10th Network and Distributed System Security Symp[C]. Berkeley: USENIX Asso-ciation, 2003.191-206.
[9]	CHRISTIAN H , SCHNEIDER H , PFOHH H . A universal semantic bridge for virtual machine introspection[A]. HICISS[C]. 2011.370-373.
[10]	DOLAN-GAVITT B , LEEK T , ZHIVICH M , et al. Virtuoso: narrow-ing the semantic gap in virtual machine introspection[A]. IEEE Sym-posium on Security and Privacy[C]. 2011.297-312.

被测程序	内在对象组数量	Sleak		Aleak	总泄漏数
被测程序	内在对象组数量	Suspected	Leak	Aleak	总泄漏数
ProFTPD	57	27	5	3	11
Squid	79	31	7	2	13

被测程序	完成分组时间	Aleak检测时间	Sleak检测时间	嫌疑的内存泄漏确认时间
ProFTPD	31	2.3	1.6	1.1
Squid	55	2.1	2.3	2.1

被测程序	null	Open/close	read	write
Xen+ProFTPD	0.55	13.3	2.3	2.1
Xen+Squid	0.56	14.2	2.3	1.8
Xen+VMLD+ProFTPD	5.71	17.3	4.6	6.1
Xen+VMLD+Squid	6.13	22.1	4.3	6.1

[1]	冯竞舸, 贺也平, 陶秋铭. 自动向量化：近期进展与展望[J]. 通信学报, 2022, 43(3): 180-195.
[2]	李冲, 杜秀娟, 王丽娟, 田晓静. 基于规则与感知的水声网络MAC协议[J]. 通信学报, 2022, 43(2): 65-75.
[3]	黎赛, 杨亮, 崔琪楣, 于思源. RIS辅助的混合RF/THz系统性能分析[J]. 通信学报, 2022, 43(1): 49-58.
[4]	宋宇波, 陈琪, 宋睿, 胡爱群. 基于虚拟机字节码注入的Android应用程序隐私保护机制[J]. 通信学报, 2021, 42(6): 171-181.
[5]	王文鼐, 张延贺, 吴炜, 柏琛, 王斌. 分布式排队中退避树的深度优先遍历算法[J]. 通信学报, 2021, 42(2): 72-80.
[6]	伏玉笋,杨根科. 人工智能在移动通信中的应用：挑战与实践[J]. 通信学报, 2020, 41(9): 190-201.
[7]	官铮,熊磊,贾徭,何敏,杨志军. RoF-DAS架构下具有差错重传的预约式WLAN MAC协议研究[J]. 通信学报, 2020, 41(3): 102-111.
[8]	李梓杨,于炯,王跃飞,卞琛,蒲勇霖,张译天,刘宇. Flink环境下基于负载预测的弹性资源调度策略[J]. 通信学报, 2020, 41(10): 92-108.
[9]	杨震,朱梦瑶,冯友宏. 认知协作NOMA网络的安全性能分析[J]. 通信学报, 2020, 41(10): 139-147.
[10]	黄开枝,潘启润,袁泉,游伟,汤红波. 基于性能感知的网络切片部署方法[J]. 通信学报, 2019, 40(8): 114-122.
[11]	李晖,叶铭,童强,程杰,王力杰. 系统极化码和非系统极化码的性能比较[J]. 通信学报, 2019, 40(6): 203-209.
[12]	简鑫,王芳,宋健,付澍,谭晓衡,曾孝平. 带冲突检测的两阶段无连接接入协议最优资源分配[J]. 通信学报, 2019, 40(5): 117-124.
[13]	何欣枫,田俊峰,刘凡鸣. 可信云平台技术综述[J]. 通信学报, 2019, 40(2): 154-163.
[14]	金伟,余铭洁,李凤华,杨正坤,耿魁. 支持高并发的Hadoop高性能加密方法研究[J]. 通信学报, 2019, 40(12): 29-40.
[15]	田俊峰, 王子龙, 何欣枫, 李珍. 基于Shamir的虚拟机放置策略[J]. 通信学报, 2019, 40(10): 90-100.