TY - GEN
T1 - Mbrace
T2 - 7th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2009
AU - Van Der Zee, Andrej
AU - Courbot, Alexandre
AU - Nakajima, Tatsuo
PY - 2009/12/3
Y1 - 2009/12/3
N2 - Today's monitoring tools and web application middleware offer very limited support for detailed performance analysis of HTTP request-based, multi-tier web applications. They measure resource usage system-wide or per command name, but are unable to isolate usage per action specific to the target application1. This inability has several causes: First, many HTTP requests are executed by one application or script simultaneously, making it hard to isolate them. Second, it is difficult to monitor at the granularity of a thread, while efficient web servers and database servers implement threadbased process models. Third, different types of actions are often handled by one application or script, hindering typebased distinction. Finally, existing tools are often intervalbased, consequently missing short-lived processes that live between two capturing points. The same limitations apply to measuring individual SQL queries. In addition, SQL queries cannot be backtracked to the HTTP request that triggered them, even though they frequently turn out to be the cause of long end-to-end response times. This paper describes a preliminary solution that addresses these problems and enables us to measure resource consumption and database interaction for individual actions, in real-time and under load, with minimal effort from the web application developer.
AB - Today's monitoring tools and web application middleware offer very limited support for detailed performance analysis of HTTP request-based, multi-tier web applications. They measure resource usage system-wide or per command name, but are unable to isolate usage per action specific to the target application1. This inability has several causes: First, many HTTP requests are executed by one application or script simultaneously, making it hard to isolate them. Second, it is difficult to monitor at the granularity of a thread, while efficient web servers and database servers implement threadbased process models. Third, different types of actions are often handled by one application or script, hindering typebased distinction. Finally, existing tools are often intervalbased, consequently missing short-lived processes that live between two capturing points. The same limitations apply to measuring individual SQL queries. In addition, SQL queries cannot be backtracked to the HTTP request that triggered them, even though they frequently turn out to be the cause of long end-to-end response times. This paper describes a preliminary solution that addresses these problems and enables us to measure resource consumption and database interaction for individual actions, in real-time and under load, with minimal effort from the web application developer.
UR - http://www.scopus.com/inward/record.url?scp=70749114644&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70749114644&partnerID=8YFLogxK
U2 - 10.1109/CSE.2009.219
DO - 10.1109/CSE.2009.219
M3 - Conference contribution
AN - SCOPUS:70749114644
SN - 9780769538235
T3 - Proceedings - 12th IEEE International Conference on Computational Science and Engineering, CSE 2009
SP - 166
EP - 173
BT - Proceedings - 12th IEEE International Conference on Computational Science and Engineering, CSE 2009 - 7th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, EUC 2009
Y2 - 29 August 2009 through 31 August 2009
ER -