Results 1 - 10
of
15
Data center demand response: Avoiding the coincident peak via workload shifting and local generation
- In ACM SIGMETRICS
, 2013
"... Demand response is a crucial aspect of the future smart grid. It has the potential to provide significant peak demand reduction and to ease the incorporation of renewable energy into the grid. Data centers ’ participation in demand response is becoming increasingly important given their high and inc ..."
Abstract
-
Cited by 32 (3 self)
- Add to MetaCart
(Show Context)
Demand response is a crucial aspect of the future smart grid. It has the potential to provide significant peak demand reduction and to ease the incorporation of renewable energy into the grid. Data centers ’ participation in demand response is becoming increasingly important given their high and increasing energy consumption and their flexibility in demand management compared to conventional industrial facilities. In this paper, we study two demand response schemes to reduce a data center’s peak loads and energy expenditure: workload shifting and the use of local power generations. We conduct a detailed characterization study of coincident peak data over two decades from Fort Collins Utilities, Colorado and then develop two optimization based algorithms by combining workload scheduling and local power generation to avoid the coincident peak and reduce the energy expenditure. The first algorithm optimizes the expected cost and the second one provides the optimal worst-case guarantee. We evaluate these algorithms via trace-based simulations. The results show that using workload shifting in combination with local generation can provide significant cost savings compared to either alone. 1.
Dreamweaver: architectural support for deep sleep
- In ASPLOS ’12
"... Numerous data center services exhibit low average utilization lead-ing to poor energy efficiency. Although CPU voltage and frequency scaling historically has been an effective means to scale down power with utilization, transistor scaling trends are limiting its effectiveness and the CPU is accounti ..."
Abstract
-
Cited by 15 (1 self)
- Add to MetaCart
(Show Context)
Numerous data center services exhibit low average utilization lead-ing to poor energy efficiency. Although CPU voltage and frequency scaling historically has been an effective means to scale down power with utilization, transistor scaling trends are limiting its effectiveness and the CPU is accounting for a shrinking fraction of system power. Recent research advocates the use of full-system idle low-power modes to combat energy losses, as such modes pro-vide the deepest power savings with bounded response time impact. However, the trend towards increasing cores per die is undermin-ing the effectiveness of these sleep modes, particularly for request-parallel data center applications, because the independent idle pe-riods across individual cores are unlikely to align by happenstance. We propose DreamWeaver, architectural support to facilitate deep sleep for request-parallel applications on multicore servers. DreamWeaver comprises two elements: Weave Scheduling, a scheduling policy to coalesce idle and busy periods across cores to create opportunities for system-wide deep sleep; and the Dream Processor, a light-weight co-processor that monitors incoming net-work traffic and suspended work during sleep to determine when the system must wake. DreamWeaver is based on two key con-cepts: (1) stall execution and sleep anytime any core is unoccu-pied, but (2) constrain the maximum time any request may be stalled. Unlike prior scheduling approaches, DreamWeaver will preempt execution to sleep, maximizing time spent at the systems’ most efficient operating point. We demonstrate that DreamWeaver can smoothly trade-off bounded, predictable increases in 99th-percentile response time for increasing power savings, and strictly dominates the savings available with voltage and frequency scaling and timeout-based request batching schemes.
Reconciling high server utilization and sub-millisecond quality-of-service
- In European Conference on Computer Systems (EuroSys
, 2014
"... The simplest strategy to guarantee good quality of service (QoS) for a latency-sensitive workload with sub-millisecond latency in a shared cluster environment is to never run other workloads concurrently with it on the same server. Unfortu-nately, this inevitably leads to low server utilization, red ..."
Abstract
-
Cited by 11 (4 self)
- Add to MetaCart
(Show Context)
The simplest strategy to guarantee good quality of service (QoS) for a latency-sensitive workload with sub-millisecond latency in a shared cluster environment is to never run other workloads concurrently with it on the same server. Unfortu-nately, this inevitably leads to low server utilization, reduc-ing both the capability and cost effectiveness of the cluster. In this paper, we analyze the challenges of maintaining high QoS for low-latency workloads when sharing servers with other workloads. We show that workload co-location leads to QoS violations due to increases in queuing delay, scheduling delay, and thread load imbalance. We present techniques that address these vulnerabilities, ranging from provisioning the latency-critical service in an interference aware manner, to replacing the Linux CFS scheduler with a scheduler that provides good latency guarantees and fair-ness for co-located workloads. Ultimately, we demonstrate that some latency-critical workloads can be aggressively co-located with other workloads, achieve good QoS, and that such co-location can improve a datacenter’s effective throughput per TCO- $ by up to 52%. 1.
ECHO: Recreating Network Traffic Maps for Datacenters with Tens of Thousands of Servers
"... Abstract—Large-scale datacenters now host a large part of the world’s data and computation, which makes their design a crucial architectural challenge. Datacenter (DC) applications, unlike traditional workloads, are dominated by user patterns that only emerge in the large-scale. This creates the nee ..."
Abstract
-
Cited by 5 (3 self)
- Add to MetaCart
(Show Context)
Abstract—Large-scale datacenters now host a large part of the world’s data and computation, which makes their design a crucial architectural challenge. Datacenter (DC) applications, unlike traditional workloads, are dominated by user patterns that only emerge in the large-scale. This creates the need for concise, accurate and scalable analytical models that capture both their temporal and spatial features and can be used to create representative activity patterns. Unfortunately, previous work lacks the ability to track the complex patterns that are present in these applications, or scales poorly with the size of the system. In this work, we focus on the network aspect of datacenter workloads. We present ECHO, a scalable and accurate modeling scheme that uses hierarchical Markov Chains to capture the network activity of large-scale applications in time and space. ECHO can also use these models to re-create representative network traffic patterns. We validate the model against real DC-scale applications, such as Websearch and show marginal deviations between original and generated workloads. We verify that ECHO captures all the critical features of DC workloads, such as the locality of communication and burstiness and evaluate the granularity necessary for this. Finally we perform a detailed characterization of the network traffic for workloads in DCs of tens of thousands of servers over significant time frames. I.
SleepScale: Runtime Joint Speed Scaling and Sleep States Management for Power Efficient Data Centers
- in Proceeding of the 41st Annual International Symposium on Computer Architecuture, ser. ISCA ’14. Piscataway, NJ
, 2014
"... Power consumption in data centers has been growing sig-nificantly in recent years. To reduce power, servers are being equipped with increasingly sophisticated power management mechanisms. Different mechanisms offer dramatically differ-ent trade-offs between power savings and performance penal-ties. ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Power consumption in data centers has been growing sig-nificantly in recent years. To reduce power, servers are being equipped with increasingly sophisticated power management mechanisms. Different mechanisms offer dramatically differ-ent trade-offs between power savings and performance penal-ties. Considering the complexity, variety, and temporally-varying nature of the applications hosted in a typical data center, intelligently determining which power management policy to use and when is a complicated task. In this paper we analyze a system model featuring both performance scaling and low-power states. We reveal the interplay between performance scaling and low-power states via intensive simulation and analytic verification. Based on the observations, we present SleepScale, a runtime power management tool designed to efficiently exploit existing power control mechanisms. At run time, SleepScale characterizes power consumption and quality-of-service (QoS) for each low-power state and frequency setting, and selects the best policy for a given QoS constraint. We evaluate SleepScale using workload traces from data centers and achieve significant power savings relative to conventional power management strategies. 1.
Hybrid Simulation of CyberPhysical Energy Systems
"... Abstract—Simulating cyber-physical energy systems such as data centers requires the characterization of the energy interactions between the computing units and the physical environment. Such interactions involve discrete events such as changes in operating modes of cooling units, and also transient ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract—Simulating cyber-physical energy systems such as data centers requires the characterization of the energy interactions between the computing units and the physical environment. Such interactions involve discrete events such as changes in operating modes of cooling units, and also transient processes such as heat flow. An event-based simulator fails to capture continuous transient effects while a time-stepped simulation can ignore events occurring within the decision interval. This paper proposes an error-bound hybrid simulator that integrates discrete event-driven (ED) simulation and finite-horizon time based simulation (FHT) and simulates energy interactions in a cyber-physical energy system. We apply this simulator to a data center case and validate the simulation results by comparing them with simulations performed in previous literature. We also evaluate the accuracy of the simulator by comparing the test case results with realistic data obtained from a real data center deployment. The error bound of the simulator is a user input and influences the time interval of the ED and FHT modules. I.
Implications of High Energy Proportional Servers on Cluster-Wide Energy Proportionality
- In Proceedings of the International Symposium on High Performance Computer Architecture, HPCA, 2014. Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS14, held as part of SC14
, 2014
"... Cluster-level packing techniques have long been used to improve the energy proportionality of server clusters by masking the poor energy proportionality of individual servers. With the emergence of high energy proportional servers, we revisit whether cluster-level packing techniques are still the mo ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
Cluster-level packing techniques have long been used to improve the energy proportionality of server clusters by masking the poor energy proportionality of individual servers. With the emergence of high energy proportional servers, we revisit whether cluster-level packing techniques are still the most effective way to achieve high cluster-wide energy proportionality. Our findings indicate that cluster-level packing techniques can eventually limit cluster-wide energy proportionality and it may be more beneficial to de-pend solely on server-level low power techniques. Server-level low power techniques generally require a high la-tency slack to be effective due to diminishing idle periods as server core count increases. In order for server-level low power techniques to be a viable alternative, the la-tency slack required for these techniques must be lowered. We found that server-level active low power modes offer the lowest latency slack, independent of server core count, and propose low power mode switching policies to meet the best-case latency slack under realistic conditions. By over-coming these major issues, we show that server-level low power modes can be a viable alternative to cluster-level packing techniques in providing high cluster-wide energy proportionality. 1.
Scalable System-level Active Low-Power Mode with Bounded Latency
"... Many system-level inactive low power modes exploit idle pe-riods to obtain energy savings. With the emergence of mul-ticore servers, idle periods are becoming increasingly rare. In order to save energy in multicore servers, low-utilization periods, which remains with increasing core count, must be e ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Many system-level inactive low power modes exploit idle pe-riods to obtain energy savings. With the emergence of mul-ticore servers, idle periods are becoming increasingly rare. In order to save energy in multicore servers, low-utilization periods, which remains with increasing core count, must be exploited. Server-level heterogenous servers, such as Knight-Shift, have been shown to significantly improve the energy proportionality of datacenter servers through exploiting low-utilization periods. However, previous switching policies, which decides when to switch between a high-power high-performance node and a low-power lower-performance node, are simplistic and easily fooled by server utilization patterns, leading to false switches and thrashing causing unbounded latency impact. In this paper, we propose Hueristic-based Switching Policies (HSP), which uses utilization history to predict when fu-ture high utilization periods will occur. We show that HSP can significantly reduce thrashing and false switches, bound-ing latency while still maintaining significant energy savings. Furthermore, we show that active low-power modes that exploit low utilization periods are able to sustain energy-latency tradeoffs as core count increases and offer superior energy savings compared to idleness scheduling algorithms.
Towards Building Wind Tunnels for Data Center Design
"... Data center design is a tedious and expensive process. Recently, this process has become even more challenging as users of cloud services expect to have guaranteed levels of availability, durability and performance. A new challenge for the service providers is to find the most cost-effective data ce ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Data center design is a tedious and expensive process. Recently, this process has become even more challenging as users of cloud services expect to have guaranteed levels of availability, durability and performance. A new challenge for the service providers is to find the most cost-effective data center design and configuration that will accommodate the users ’ expectations, on ever-changing workloads, and constantly evolving hardware and software components. In this paper, we argue that data center design should become a systematic process. First, it should be done using an integrated approach that takes into account both the hardware and the software interdependencies, and their impact on users ’ expectations. Second, it should be performed in a “wind tunnel”, which uses large-scale simulation to systematically explore the impact of a data center configuration on both the users ’ and the service providers ’ requirements. We believe that this is the first step towards systematic data center design – an exciting area for future research. 1.
Data Center Architectures: Challenges and Opportunities
"... Recently, data centers became a main part in information and communication technology. Data centers are facing many challenges because of the rapid and continuous growth of applications ’ size and complexity. In this paper, we present an overview of data center architectures challenges and their pro ..."
Abstract
- Add to MetaCart
(Show Context)
Recently, data centers became a main part in information and communication technology. Data centers are facing many challenges because of the rapid and continuous growth of applications ’ size and complexity. In this paper, we present an overview of data center architectures challenges and their proposed solutions related to networking equipment, information technology equipment, power conservation equipment as well as cooling systems. We also mentioned how software defined network, a promising technology, can enhance the performance of data centers, and what challenges are faced while applying such technology to existing data centers.
