计算机科学 ›› 2025, Vol. 52 ›› Issue (6A): 240800023-6.doi: 10.11896/jsjkx.240800023
魏书文, 王宝会
WEI Shuwen, WANG Baohui
摘要： 缺页异常处理是Linux内核内存管理子系统中的核心模块,对于数据库等内存密集型应用,其处理效率直接影响全系统性能,常常成为性能瓶颈。优化内存使用和减少缺页异常发生已经有大量的研究工作,但在实际环境下缺页异常的处理模式及其延迟分布却鲜有人关注。文中提出了一种基于执行跟踪的方法,用于分析缺页异常的处理模式及其延迟分布,通过该方法,提出了两种经典内存密集型负载的缺页异常的处理模式及其延迟分布,为优化内存密集型应用提供了重要参考。
中图分类号:
| [1]CHO S,CHO Y.Page fault behavior and two prepaging schemes[C]//Conference Proceedings of the 1996 IEEE Fifteenth Annual International Phoenix Conference onComputers and Communications.IEEE,1996:15-21. [2]MUTHUSUNDARI S,BERLIN M A,GEETHA P.A bufferbased page replacementalgorithm to reduce page fault[J].Materials Today:Proceedings,2020,33:4557-4560. [3]TIRUMALASETTY C,CHOU C C,REDDY N,et al.Reducing minor page fault overheads through enhanced page walker[J].ACM Transactions on Architecture and Code Optimization(TACO),2022,19(4):1-26. [4]GANNON D,JALBY W,GALLIVAN K.Strategies for cacheand local memory management by global program transformation[C]//International Conference on Supercomputing.Berlin,Heidelberg:Springer Berlin Heidelberg,1987. [5]CHU W W,OPDERBECK H.Program behavior and the page-fault-frequency replacement algorithm[J].Computer,1976,9(11):29-38. [6]GREGG B.Linux Performance[EB／OL].https://www.bre-ndangregg.com/Slides/Percona2018_Linux_Performance.pdf. [7]LOUKIDES M K.System performance tuning[M].O’Reilly & Associates,Inc.,1996. [8]BIRD T.Measuring function duration with ftrace[C]//Procee-dings of the Linux Symposium.Ottawa,ON,Canada:Citeseer,2009,1. [9]GHOSH S,HAMOU-LHADJ A,EZZATI-JIVAN N.Systemand Application Performance Analysis Patterns Using Software Tracing[D].Montreal Concordia University,2022. [10]LAROSA C,XIONG L,MANDELBERG K.Frequent patternmining for kernel trace data[C]//Proceedings of the 2008 ACM Symposium on Applied Computing.2008:880-885. [11]CHO H,EGGER B,LEE J,et al.Dynamic data scratchpadmemory management for a memory subsystem with an MMU[C]//Proceedings of the 2007 ACM SIGPLAN/SIGBED Conference on Languages,Compilers,and Tools for Embedded Systems.2007. [12]HAN J,KAMBER M.Data Mining:Concepts and Techniques(nd ed)[M].San Francisco,CA:Morgan Kaufmann Publishers. [13]JIAN P,HAN J,MORTAZAVI-ASL B,et al.Prefixspan:Mining sequential patterns efficiently by prefix-projected pattern growth[C]//Proceedings of the 17th International Conference on Data Engineering.IEEE,2001. [14]LEHMANN R.Redis in the yahoo! cloud serving benchmark[R].Cloud Serving Benchmark,2011. [15]LEUTENEGGER S T,DIAS D.A modeling study of the TPC-C benchmark[J].ACM Sigmod Record,1993,22(2):22-31. [16]CROTTY A,LEIS V,PAVLO A.Are you sure you want to use mmap in your database management system?[C]//Conference on Innovative Data Systems Research(CIDR).2022. [17]SANTHOSH K T , MISHR A D, PAND A B,et al.CoW-Light:Hardware assisted copy-on-write fault handling for secure deduplication[C]//Proceedings of the 8th International Workshop on Hardware and Architectural Support for Security and Privacy.2019. [18]HUANG J,QURESHI M K,SCHWAN K.An evolutionarystudy of Linux memory management for fun and profit[C]//Proceedings of the 2016 USENIX Annual Technical Conference(USENIX ATC 16).2016. [19]HUNTER A H,CAPITAL J S, KENNELLY C,et al.Beyond malloc efficiency to fleet efficiency:a hugepage-aware memory allocator[C]//Proceedings of the 15th USENIX Symposium on Operating Systems Design and Implementation(OSDI 21).2021. [20]KIM J,CHOE W,AHN J.“Exploring the design space of page management for Multi-Tiered memory systems”[C]//Procee-dings of the 2021 USENIX Annual Technical Conference(USENIX ATC 21).2021. [21]LESOKHIN I ,ERAN H, RAINDEL S,et al.Page fault support for network controllers[J].ACM SIGARCH Computer Architecture News,2017,45(1):449-466. |
|
||
首页