Detailed characterization of a Quad Pentium Pro server running TPC-D

Q. Cao, P. Trancoso, J. L. Larriba-Pey, J. Torrellas, R. Knighten, Y. Won

Research output: Contribution to conferencePaper

Abstract

While database workloads consume a major fraction of the cycles in today's machines, there are only a few public-domain performance studies that characterize in detail how these workloads exercise the machines. This fact is due to the complexity of setting up and tuning database workloads, the high cost of the equipment required to evaluate them, and the frequent use of proprietary systems. In this paper, we help redress this problem by presenting a detailed performance characterization of the TPC-D benchmark running on a 4-processor Pentium Pro SMP multiprocessor with Windows NT and Microsoft's SQL Server. We use the Pentium Pro built-in hardware event counters and software tools that monitor system activity. Our results show that TPC-D queries have a relatively low CPI. The CPIs, which are 1.27 on average for the 17 read-only queries, are comparable to values observed for technical workloads. The major sources of processor stall cycles are the instruction fetch bottleneck and data misses in the secondary cache. Kernel time is negligible, as queries spend less than 6% of their time on average in the kernel. Other results show that branch prediction is effective in TPC-D and that the exclusive state in the cache tags is largely unnecessary. Finally, we compare our results to the ones published for TPC-C.

Original languageEnglish (US)
Pages108-115
Number of pages8
StatePublished - Dec 1 1999
EventInternational Conference on Computer Design (ICCD'99) - Austin, TX, USA
Duration: Oct 10 1999Oct 13 1999

Other

OtherInternational Conference on Computer Design (ICCD'99)
CityAustin, TX, USA
Period10/10/9910/13/99

Fingerprint

Servers
Computer hardware
Tuning
Costs

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Cao, Q., Trancoso, P., Larriba-Pey, J. L., Torrellas, J., Knighten, R., & Won, Y. (1999). Detailed characterization of a Quad Pentium Pro server running TPC-D. 108-115. Paper presented at International Conference on Computer Design (ICCD'99), Austin, TX, USA, .

Detailed characterization of a Quad Pentium Pro server running TPC-D. / Cao, Q.; Trancoso, P.; Larriba-Pey, J. L.; Torrellas, J.; Knighten, R.; Won, Y.

1999. 108-115 Paper presented at International Conference on Computer Design (ICCD'99), Austin, TX, USA, .

Research output: Contribution to conferencePaper

Cao, Q, Trancoso, P, Larriba-Pey, JL, Torrellas, J, Knighten, R & Won, Y 1999, 'Detailed characterization of a Quad Pentium Pro server running TPC-D' Paper presented at International Conference on Computer Design (ICCD'99), Austin, TX, USA, 10/10/99 - 10/13/99, pp. 108-115.
Cao Q, Trancoso P, Larriba-Pey JL, Torrellas J, Knighten R, Won Y. Detailed characterization of a Quad Pentium Pro server running TPC-D. 1999. Paper presented at International Conference on Computer Design (ICCD'99), Austin, TX, USA, .
Cao, Q. ; Trancoso, P. ; Larriba-Pey, J. L. ; Torrellas, J. ; Knighten, R. ; Won, Y. / Detailed characterization of a Quad Pentium Pro server running TPC-D. Paper presented at International Conference on Computer Design (ICCD'99), Austin, TX, USA, .8 p.
@conference{1ced6758ac064cf595b92d1a8eb01a99,
title = "Detailed characterization of a Quad Pentium Pro server running TPC-D",
abstract = "While database workloads consume a major fraction of the cycles in today's machines, there are only a few public-domain performance studies that characterize in detail how these workloads exercise the machines. This fact is due to the complexity of setting up and tuning database workloads, the high cost of the equipment required to evaluate them, and the frequent use of proprietary systems. In this paper, we help redress this problem by presenting a detailed performance characterization of the TPC-D benchmark running on a 4-processor Pentium Pro SMP multiprocessor with Windows NT and Microsoft's SQL Server. We use the Pentium Pro built-in hardware event counters and software tools that monitor system activity. Our results show that TPC-D queries have a relatively low CPI. The CPIs, which are 1.27 on average for the 17 read-only queries, are comparable to values observed for technical workloads. The major sources of processor stall cycles are the instruction fetch bottleneck and data misses in the secondary cache. Kernel time is negligible, as queries spend less than 6{\%} of their time on average in the kernel. Other results show that branch prediction is effective in TPC-D and that the exclusive state in the cache tags is largely unnecessary. Finally, we compare our results to the ones published for TPC-C.",
author = "Q. Cao and P. Trancoso and Larriba-Pey, {J. L.} and J. Torrellas and R. Knighten and Y. Won",
year = "1999",
month = "12",
day = "1",
language = "English (US)",
pages = "108--115",
note = "International Conference on Computer Design (ICCD'99) ; Conference date: 10-10-1999 Through 13-10-1999",

}

TY - CONF

T1 - Detailed characterization of a Quad Pentium Pro server running TPC-D

AU - Cao, Q.

AU - Trancoso, P.

AU - Larriba-Pey, J. L.

AU - Torrellas, J.

AU - Knighten, R.

AU - Won, Y.

PY - 1999/12/1

Y1 - 1999/12/1

N2 - While database workloads consume a major fraction of the cycles in today's machines, there are only a few public-domain performance studies that characterize in detail how these workloads exercise the machines. This fact is due to the complexity of setting up and tuning database workloads, the high cost of the equipment required to evaluate them, and the frequent use of proprietary systems. In this paper, we help redress this problem by presenting a detailed performance characterization of the TPC-D benchmark running on a 4-processor Pentium Pro SMP multiprocessor with Windows NT and Microsoft's SQL Server. We use the Pentium Pro built-in hardware event counters and software tools that monitor system activity. Our results show that TPC-D queries have a relatively low CPI. The CPIs, which are 1.27 on average for the 17 read-only queries, are comparable to values observed for technical workloads. The major sources of processor stall cycles are the instruction fetch bottleneck and data misses in the secondary cache. Kernel time is negligible, as queries spend less than 6% of their time on average in the kernel. Other results show that branch prediction is effective in TPC-D and that the exclusive state in the cache tags is largely unnecessary. Finally, we compare our results to the ones published for TPC-C.

AB - While database workloads consume a major fraction of the cycles in today's machines, there are only a few public-domain performance studies that characterize in detail how these workloads exercise the machines. This fact is due to the complexity of setting up and tuning database workloads, the high cost of the equipment required to evaluate them, and the frequent use of proprietary systems. In this paper, we help redress this problem by presenting a detailed performance characterization of the TPC-D benchmark running on a 4-processor Pentium Pro SMP multiprocessor with Windows NT and Microsoft's SQL Server. We use the Pentium Pro built-in hardware event counters and software tools that monitor system activity. Our results show that TPC-D queries have a relatively low CPI. The CPIs, which are 1.27 on average for the 17 read-only queries, are comparable to values observed for technical workloads. The major sources of processor stall cycles are the instruction fetch bottleneck and data misses in the secondary cache. Kernel time is negligible, as queries spend less than 6% of their time on average in the kernel. Other results show that branch prediction is effective in TPC-D and that the exclusive state in the cache tags is largely unnecessary. Finally, we compare our results to the ones published for TPC-C.

UR - http://www.scopus.com/inward/record.url?scp=0033296816&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033296816&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0033296816

SP - 108

EP - 115

ER -