TY - GEN
T1 - DIMMer
T2 - 5th ACM Symposium on Cloud Computing, SOCC 2014
AU - Zhang, Dongli
AU - Ehsan, Moussa
AU - Ferdman, Michael
AU - Sion, Radu
N1 - Publisher Copyright:
Copyright © 2014 by the Association for Computing Machinery, Inc. (ACM).
PY - 2014/11/3
Y1 - 2014/11/3
N2 - Lack of energy proportionality in server systems results in significant waste of energy when operating at low utilization, a common scenario in today's data centers. We propose DIMMer, an approach to eliminate the idle power consumption of unused system components, motivated by two key observations. First, even in their lowest-power states, the power consumption of server components remains significant. Second, unused components can be powered off entirely without sacrificing server availability. We demonstrate that unused memory capacity can be powered off, eliminating the energy waste of self-refresh for unallocated memory, while still allowing for all capacity to be available on a moment's notice. Similarly, only one CPU socket must remain powered on, allowing unused CPUs and attached memory to be powered off entirely. The DIMMer vision can improve energy proportionality and achieve energy savings. Using a Google cluster trace as well as in-house experiments, we estimate up to 50% savings on DRAM and 18.8% on CPU background energy. At $0.10/kWh, this corresponds to 0.6% of total data center cost.
AB - Lack of energy proportionality in server systems results in significant waste of energy when operating at low utilization, a common scenario in today's data centers. We propose DIMMer, an approach to eliminate the idle power consumption of unused system components, motivated by two key observations. First, even in their lowest-power states, the power consumption of server components remains significant. Second, unused components can be powered off entirely without sacrificing server availability. We demonstrate that unused memory capacity can be powered off, eliminating the energy waste of self-refresh for unallocated memory, while still allowing for all capacity to be available on a moment's notice. Similarly, only one CPU socket must remain powered on, allowing unused CPUs and attached memory to be powered off entirely. The DIMMer vision can improve energy proportionality and achieve energy savings. Using a Google cluster trace as well as in-house experiments, we estimate up to 50% savings on DRAM and 18.8% on CPU background energy. At $0.10/kWh, this corresponds to 0.6% of total data center cost.
KW - Cloud computing
KW - DRAM
KW - Energy
UR - https://www.scopus.com/pages/publications/85118316218
U2 - 10.1145/2670979.2670990
DO - 10.1145/2670979.2670990
M3 - Conference contribution
AN - SCOPUS:85118316218
T3 - Proceedings of the 5th ACM Symposium on Cloud Computing, SOCC 2014
BT - Proceedings of the 5th ACM Symposium on Cloud Computing, SOCC 2014
PB - Association for Computing Machinery
Y2 - 3 November 2014 through 5 November 2014
ER -