Characterization, monitoring and evaluation of operational performance trends on server processor hardware

Ernest Sithole, Sally McClean, Scotney Bryan, Gerard Parr, Moore Adrian, David Bustard, Stephen Dawson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Enterprise IT environments have seen a sharp growth in content use due to the popularity of on-demand data-intensive applications. In turn, the huge demand in content has spawned off major developments such as growth and distribution of computing nodes as well as the adoption of various implementation technologies. Given the complexity brought to the makeup of business computing environments in addressing the above-mentioned factors, the critical planning task of determining the appropriate infrastructure sizes for supporting firm Quality of Service (QoS) guarantees becomes a very challenging undertaking to fulfil. Benchmarking methods are widely employed in calibrating attainable performance in IT solutions, but these have the drawback of presenting output performance metrics as composite measurements that only give an end-to-end perspective. As an enhancement to benchmarking approaches, we explore the use of Performance Monitoring Counters (PMCs) in obtaining detailed operational performance of CPU and memory hardware. Performance Monitoring Counters (PMCs) are onchip registers found on most modern processor hardware. We use PMC-derived measurements to validate cache performance trends that have been derived analytically, and in the course of validations, PMC data is also used to investigate the nature and character of surges in cache miss events, which emerge as the memory load generated by runtime processes increases.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages391-402
Number of pages12
DOIs
Publication statusPublished - 14 Mar 2011
EventICPE '11 the second joint WOSP/SIPEW international conference on Performance engineering - Karlsruhe, Germany
Duration: 14 Mar 2011 → …

Conference

ConferenceICPE '11 the second joint WOSP/SIPEW international conference on Performance engineering
Period14/03/11 → …

Fingerprint

Computer hardware
Servers
Monitoring
Benchmarking
Data storage equipment
Program processors
Industry
Quality of service
Hardware
Planning
Composite materials

Cite this

Sithole, Ernest ; McClean, Sally ; Bryan, Scotney ; Parr, Gerard ; Adrian, Moore ; Bustard, David ; Dawson, Stephen. / Characterization, monitoring and evaluation of operational performance trends on server processor hardware. Unknown Host Publication. 2011. pp. 391-402
@inproceedings{0fb37154348c4b99bde23dc8122895b9,
title = "Characterization, monitoring and evaluation of operational performance trends on server processor hardware",
abstract = "Enterprise IT environments have seen a sharp growth in content use due to the popularity of on-demand data-intensive applications. In turn, the huge demand in content has spawned off major developments such as growth and distribution of computing nodes as well as the adoption of various implementation technologies. Given the complexity brought to the makeup of business computing environments in addressing the above-mentioned factors, the critical planning task of determining the appropriate infrastructure sizes for supporting firm Quality of Service (QoS) guarantees becomes a very challenging undertaking to fulfil. Benchmarking methods are widely employed in calibrating attainable performance in IT solutions, but these have the drawback of presenting output performance metrics as composite measurements that only give an end-to-end perspective. As an enhancement to benchmarking approaches, we explore the use of Performance Monitoring Counters (PMCs) in obtaining detailed operational performance of CPU and memory hardware. Performance Monitoring Counters (PMCs) are onchip registers found on most modern processor hardware. We use PMC-derived measurements to validate cache performance trends that have been derived analytically, and in the course of validations, PMC data is also used to investigate the nature and character of surges in cache miss events, which emerge as the memory load generated by runtime processes increases.",
author = "Ernest Sithole and Sally McClean and Scotney Bryan and Gerard Parr and Moore Adrian and David Bustard and Stephen Dawson",
year = "2011",
month = "3",
day = "14",
doi = "10.1145/1958746.1958801",
language = "English",
pages = "391--402",
booktitle = "Unknown Host Publication",

}

Sithole, E, McClean, S, Bryan, S, Parr, G, Adrian, M, Bustard, D & Dawson, S 2011, Characterization, monitoring and evaluation of operational performance trends on server processor hardware. in Unknown Host Publication. pp. 391-402, ICPE '11 the second joint WOSP/SIPEW international conference on Performance engineering, 14/03/11. https://doi.org/10.1145/1958746.1958801

Characterization, monitoring and evaluation of operational performance trends on server processor hardware. / Sithole, Ernest; McClean, Sally; Bryan, Scotney; Parr, Gerard; Adrian, Moore; Bustard, David; Dawson, Stephen.

Unknown Host Publication. 2011. p. 391-402.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Characterization, monitoring and evaluation of operational performance trends on server processor hardware

AU - Sithole, Ernest

AU - McClean, Sally

AU - Bryan, Scotney

AU - Parr, Gerard

AU - Adrian, Moore

AU - Bustard, David

AU - Dawson, Stephen

PY - 2011/3/14

Y1 - 2011/3/14

N2 - Enterprise IT environments have seen a sharp growth in content use due to the popularity of on-demand data-intensive applications. In turn, the huge demand in content has spawned off major developments such as growth and distribution of computing nodes as well as the adoption of various implementation technologies. Given the complexity brought to the makeup of business computing environments in addressing the above-mentioned factors, the critical planning task of determining the appropriate infrastructure sizes for supporting firm Quality of Service (QoS) guarantees becomes a very challenging undertaking to fulfil. Benchmarking methods are widely employed in calibrating attainable performance in IT solutions, but these have the drawback of presenting output performance metrics as composite measurements that only give an end-to-end perspective. As an enhancement to benchmarking approaches, we explore the use of Performance Monitoring Counters (PMCs) in obtaining detailed operational performance of CPU and memory hardware. Performance Monitoring Counters (PMCs) are onchip registers found on most modern processor hardware. We use PMC-derived measurements to validate cache performance trends that have been derived analytically, and in the course of validations, PMC data is also used to investigate the nature and character of surges in cache miss events, which emerge as the memory load generated by runtime processes increases.

AB - Enterprise IT environments have seen a sharp growth in content use due to the popularity of on-demand data-intensive applications. In turn, the huge demand in content has spawned off major developments such as growth and distribution of computing nodes as well as the adoption of various implementation technologies. Given the complexity brought to the makeup of business computing environments in addressing the above-mentioned factors, the critical planning task of determining the appropriate infrastructure sizes for supporting firm Quality of Service (QoS) guarantees becomes a very challenging undertaking to fulfil. Benchmarking methods are widely employed in calibrating attainable performance in IT solutions, but these have the drawback of presenting output performance metrics as composite measurements that only give an end-to-end perspective. As an enhancement to benchmarking approaches, we explore the use of Performance Monitoring Counters (PMCs) in obtaining detailed operational performance of CPU and memory hardware. Performance Monitoring Counters (PMCs) are onchip registers found on most modern processor hardware. We use PMC-derived measurements to validate cache performance trends that have been derived analytically, and in the course of validations, PMC data is also used to investigate the nature and character of surges in cache miss events, which emerge as the memory load generated by runtime processes increases.

U2 - 10.1145/1958746.1958801

DO - 10.1145/1958746.1958801

M3 - Conference contribution

SP - 391

EP - 402

BT - Unknown Host Publication

ER -