Early Experiences with KTAU on the IBM BG/L

Abstract

The influences of OS and system-specific effects on application performance are increasingly important in high performance computing. In this regard, OS kernel measurement is necessary to understand the interrelationship of system and application behavior. This can be viewed from two perspectives: kernel-wide and process-centric. An integrated methodology and framework to observe both views in HPC systems using OS kernel measurement has remained elusive. We demonstrate a new tool called KTAU (Kernel TAU) that aims to provide parallel kernel performance measurement from both perspectives. KTAU extends the TAU performance system with kernel-level monitoring, while leveraging TAU's measurement and analysis capabilities. As part of the ZeptoOS scalable operating systems project, we report early experiences using KTAU in ZeptoOS on the IBM BG/L system.

Kernel-Level Measurement for Integrated Parallel Performance Views: the KTAU Project

“…We have ported KTAU to the IBM BG/L machine [7] as part of our work on the ZeptoOS project [4,7] (KTAU is a part of the ZeptoOS distribution). We will be evaluating I/O node performance of the BG/L system, and once a ZeptoOS port is complete, KTAU will be also be used to provide kernel performance measurement and analysis for dynamically adaptive kernel configuration.…”

“…In addition to other NPB applications, we have also experimented with the LMBENCH micro-benchmark for Linux [15]. Finally, we have conducted experiments with KTAU as integrated in ZeptoOS distribution and run on the IBM BG/L machine (see [7]). …”

One-Class SVM with Privileged Information and Its Application to Malware Detection

“…From the assembly code we calculate frequencies of each command, a number of calls to external dll files. Also we use transformation of the assembly code to an image, since malwares can be visualized as grayscale images from byte files or from asm files [21], [22]: each byte is from 0 to 255 so it can be easily translated into pixel intensity. Details of the transformation can be found in [20].…”

Analysis of Linux Scheduling with VAMPIR

“…The Linux Trace Toolkit [5] collects information about processes but does not have any information about the CPU number a process is running on. There are tools that are able to instrument a kernel (like KernInst [11] or KTau [8]) that require a unique program to be written and put into the kernel. Monitoring the /proc file system [9] would be an solution but cannot provide the fine granularity needed.…”