The Experts below are selected from a list of 147 Experts worldwide ranked by ideXlab platform
Sungyong Park - One of the best experts on this subject based on the ideXlab platform.
-
Async-LCAM: a lock contention aware messenger for Ceph distributed storage system
Cluster Computing, 2019Co-Authors: Bodon Jeong, Awais Khan, Sungyong ParkAbstract:Ceph, an object-based distributed storage system, has a communication subsystem called Async messenger. In the Async messenger, a Worker thread in the thread pool is assigned to each connection in a round-robin fashion and is allowed to process all the incoming or outgoing messages from the connection. Although this thread per connection strategy is easy to implement, it has an inherent problem such that when a connection is overloaded, it results in load imbalance problem among Worker threads. In order to mitigate this problem, Multiple Worker threads can be assigned to a single connection to handle the traffic from the connection. However, this mapping structure induces another overhead related to lock contention since Multiple threads contend to access the shared resources in the connection. In this paper, we propose lock contention aware messenger ( Async-LCAM ) , a messenger that assigns Multiple Worker threads per connection and is aware of lock contention generated from the threads. By keeping track of the lock contention of each connection every interval, the Async-LCAM dynamically adds or deletes assigned threads to/from the connection in order to balance the workloads among Worker threads. The experimental results show that the Async-LCAM improves the throughput and latency of Ceph storage by up to 184 and 65%, respectively, compared to the original Async messenger.
-
Optimizing communication performance in scale-out storage system
Cluster Computing, 2019Co-Authors: Uiseok Song, Bodon Jeong, Sungyong ParkAbstract:Ceph is an object-based scale-out storage system that is widely used in the cloud computing environment due to its scalable and reliable characteristics. Although there are many factors to affect the performance of scale-out storage systems, the design of a communication subsystem plays an important role in determining the overall performance of these systems. In this paper, we first conduct an extensive analysis of communication subsystem in Ceph, which uses asynchronous messenger framework, called async messenger, for inter-component communication in the storage cluster. Then, we propose three optimization techniques to improve the performance of Ceph messenger. These include (i) deploying load balancing algorithm among Worker threads based on the amount of workloads, (ii) assigning Multiple Worker threads (we call dual Worker) per single connection to maximize the overlapping activity among threads, and (iii) using Multiple connections between storage servers to maximize bandwidth usage. The experimental results show that the optimized Ceph messenger outperforms the original messenger implementation by up to 40% in random writes with 4 K messages. Moreover, Ceph with optimized communication subsystem shows up to 13% performance improvement as compared to original Ceph.
-
Performance Optimization of Communication Subsystem in Scale-Out Distributed Storage
2017 IEEE 2nd International Workshops on Foundations and Applications of Self* Systems (FAS*W), 2017Co-Authors: Uiseok Song, Bodon Jeong, Sungyong ParkAbstract:Scale-out distributed storage systems have recently gained high attentions with the emergence of big data and cloud computing technologies. However, these storage systems sometimes suffer from performance degradation, especially when the communication subsystem is not fully optimized. The problem becomes worse as the network bandwidth and its corresponding traffic increase. In this paper, we first conduct an extensive analysis of communication subsystem in Ceph, an object-based scale-out distributed storage system. Ceph uses asynchronous messenger framework for inter-component communication in the storage cluster. Then, we propose three major optimizations to improve the performance of Ceph messenger. These include i) deploying load balancing algorithm among Worker threads based on the amount of workloads, ii) assigning Multiple Worker threads (we call dual Worker) per single connection to maximize the overlapping activity among threads, and iii) using Multiple connections between storage servers to maximize bandwidth usage, and thus reduce replication overhead. The experimental results show that the optimized Ceph messenger outperforms the original messenger implementation up to 40% in random writes with 4K messages. Moreover, Ceph with optimized communication subsystem shows up to 13% performance improvement as compared to original Ceph.
Peter Vovsha - One of the best experts on this subject based on the ideXlab platform.
-
A model for work activity schedules with synchronization for Multiple-Worker households
Transportation, 2013Co-Authors: Surabhi Gupta, Peter VovshaAbstract:This paper presents a hybrid discrete choice-duration model for work activity scheduling with interactions between Workers in a Multiple-Worker household. The model operates in discrete space with a fine level of temporal resolution. The key innovative feature of the model is the introduction of intra-household interactions through Worker schedule synchronization mechanisms. The model was estimated based on a large Household Travel Survey from the San Francisco Bay Area. The estimation results confirmed that individual work schedules for Workers in a Multiple-Worker household are subject to strong synchronization and should be modelled jointly rather than independently. In particular, Workers in the same household tend to align their schedules and create time window overlaps for joint activities before and after work. Relative strength of the synchronization mechanisms proved to be a function of the person characteristics and household composition.
-
a model for work activity schedules with synchronization for Multiple Worker households
Transportation, 2013Co-Authors: Surabhi Gupta, Peter VovshaAbstract:This paper presents a hybrid discrete choice-duration model for work activity scheduling with interactions between Workers in a Multiple-Worker household. The model operates in discrete space with a fine level of temporal resolution. The key innovative feature of the model is the introduction of intra-household interactions through Worker schedule synchronization mechanisms. The model was estimated based on a large Household Travel Survey from the San Francisco Bay Area. The estimation results confirmed that individual work schedules for Workers in a Multiple-Worker household are subject to strong synchronization and should be modelled jointly rather than independently. In particular, Workers in the same household tend to align their schedules and create time window overlaps for joint activities before and after work. Relative strength of the synchronization mechanisms proved to be a function of the person characteristics and household composition. Copyright Springer Science+Business Media New York 2013
-
model for work activity schedules with synchronization for Multiple Worker households
Transportation Research Board 92nd Annual MeetingTransportation Research Board, 2013Co-Authors: Surabhi Gupta, Peter VovshaAbstract:This paper presents a hybrid discrete choice-duration model for work activity scheduling with interactions between Workers in a Multiple-Worker household. The model operates in discrete space with a fine level of temporal resolution. Main innovative component relates to intra-household interactions that are expressed in coordination and synchronization mechanisms between the Workers. The model was estimated based on a large Household Travel Survey in the San Francisco Bay Area. The estimation results confirmed strong intra-household interactions including synchronizations for outbound and inbound commute as well as creating overlaps of available time windows for joint activities before and after work. Relative strength of the synchronization mechanisms proved to be a function of the person characteristics and household composition.
Julien Prat - One of the best experts on this subject based on the ideXlab platform.
-
Product market regulation, Firm Selection, and Unemployment
Munich Reprints in Economics, 2020Co-Authors: Gabriel Felbermayr, Julien PratAbstract:This paper analyzes the effect of product market regulation (PMR) on unemployment in a search model with heterogeneous Multiple-Worker firms. In our setup, PMR modifies the distribution of firm productivities, thereby affecting the equilibrium rate of unemployment. We distinguish between PMR related to entry costs and PMR that generates recurrent fixed costs. We find that: (i) higher entry costs raise the rate of unemployment mainly through our novel selection effect, (ii) higher fixed costs decrease unemployment through the selection effect and increase it through the competition effect analyzed in Blanchard and Giavazzi (2003, Quarterly Journal of Economics, 118, 879-907). Firm heterogeneity magnifies the impact of both types of regulatory costs. We propose econometric evidence consistent with the unemployment effects of sunk versus recurring costs.
-
Product Market Regulation, Firm Selection and Unemployment
Journal of the European Economic Association, 2011Co-Authors: Gabriel Felbermayr, Julien PratAbstract:This paper analyzes the effect of Product Market Regulation (PMR) on unemployment in a search model with heterogeneous Multiple-Worker firms. In our setup, PMR modifies the distribution of firm productivities, thereby affecting the equilibrium rate of unemployment. We distinguish between PMR related to entry costs and PMR that generates recurrent fixed costs. We find that: (i) higher entry costs raise the rate of unemployment mainly through our novel selection effect, (ii) higher fixed costs lower unemployment through the selection effect and increase it through the competition effect analyzed in Blanchard and Giavazzi (2003). We propose econometric evidence consistent with the unemployment effects of sunk versus recurring costs.
-
Employment Protection, Product Market Regulation and Firm Selection
The Economic Journal, 2007Co-Authors: Winfried Koeniger, Julien PratAbstract:Why are firm and job turnover rates so similar across OECD countries? We argue that this may be due to the joint regulation of product and labour markets. For our analysis, we build a stochastic equilibrium model with search frictions and heterogeneous Multiple-Worker firms. This allows us to distinguish firm entry and exit from hiring and firing in a model with equilibrium unemployment. We show that firing costs, sunk entry costs and bureaucratic flow costs have countervailing effects on firm and job turnover as different types of firms select to operate in the market. Copyright 2007 The Author(s). Journal compilation Royal Economic Society 2007.
-
employment protection product market regulation and firm selection
The Economic Journal, 2007Co-Authors: Winfried Koeniger, Julien PratAbstract:This paper analyzes the effect of labor and product market regulation in a dynamic stochastic equilibrium with search frictions. Modeling Multiple-Worker firms allows us to distinguish between the exit-and-entry (extensive) margin, and the hiring-and-firing (intensive) margin. We characterize analytically how both margins depend on regulation before we calibrate the model to the US economy. We find that firing costs matter most for the intensive margin. Fixed or set-up costs in the product market instead alter primarily the behavior of firms at the extensive margin. Moreover, we find important interactions between the policies through firm selection. Finally, the opposite effect of product and labor market regulation on job turnover rationalizes the empirically observed similarity of turnover rates across countries.
Bodon Jeong - One of the best experts on this subject based on the ideXlab platform.
-
Async-LCAM: a lock contention aware messenger for Ceph distributed storage system
Cluster Computing, 2019Co-Authors: Bodon Jeong, Awais Khan, Sungyong ParkAbstract:Ceph, an object-based distributed storage system, has a communication subsystem called Async messenger. In the Async messenger, a Worker thread in the thread pool is assigned to each connection in a round-robin fashion and is allowed to process all the incoming or outgoing messages from the connection. Although this thread per connection strategy is easy to implement, it has an inherent problem such that when a connection is overloaded, it results in load imbalance problem among Worker threads. In order to mitigate this problem, Multiple Worker threads can be assigned to a single connection to handle the traffic from the connection. However, this mapping structure induces another overhead related to lock contention since Multiple threads contend to access the shared resources in the connection. In this paper, we propose lock contention aware messenger ( Async-LCAM ) , a messenger that assigns Multiple Worker threads per connection and is aware of lock contention generated from the threads. By keeping track of the lock contention of each connection every interval, the Async-LCAM dynamically adds or deletes assigned threads to/from the connection in order to balance the workloads among Worker threads. The experimental results show that the Async-LCAM improves the throughput and latency of Ceph storage by up to 184 and 65%, respectively, compared to the original Async messenger.
-
Optimizing communication performance in scale-out storage system
Cluster Computing, 2019Co-Authors: Uiseok Song, Bodon Jeong, Sungyong ParkAbstract:Ceph is an object-based scale-out storage system that is widely used in the cloud computing environment due to its scalable and reliable characteristics. Although there are many factors to affect the performance of scale-out storage systems, the design of a communication subsystem plays an important role in determining the overall performance of these systems. In this paper, we first conduct an extensive analysis of communication subsystem in Ceph, which uses asynchronous messenger framework, called async messenger, for inter-component communication in the storage cluster. Then, we propose three optimization techniques to improve the performance of Ceph messenger. These include (i) deploying load balancing algorithm among Worker threads based on the amount of workloads, (ii) assigning Multiple Worker threads (we call dual Worker) per single connection to maximize the overlapping activity among threads, and (iii) using Multiple connections between storage servers to maximize bandwidth usage. The experimental results show that the optimized Ceph messenger outperforms the original messenger implementation by up to 40% in random writes with 4 K messages. Moreover, Ceph with optimized communication subsystem shows up to 13% performance improvement as compared to original Ceph.
-
Performance Optimization of Communication Subsystem in Scale-Out Distributed Storage
2017 IEEE 2nd International Workshops on Foundations and Applications of Self* Systems (FAS*W), 2017Co-Authors: Uiseok Song, Bodon Jeong, Sungyong ParkAbstract:Scale-out distributed storage systems have recently gained high attentions with the emergence of big data and cloud computing technologies. However, these storage systems sometimes suffer from performance degradation, especially when the communication subsystem is not fully optimized. The problem becomes worse as the network bandwidth and its corresponding traffic increase. In this paper, we first conduct an extensive analysis of communication subsystem in Ceph, an object-based scale-out distributed storage system. Ceph uses asynchronous messenger framework for inter-component communication in the storage cluster. Then, we propose three major optimizations to improve the performance of Ceph messenger. These include i) deploying load balancing algorithm among Worker threads based on the amount of workloads, ii) assigning Multiple Worker threads (we call dual Worker) per single connection to maximize the overlapping activity among threads, and iii) using Multiple connections between storage servers to maximize bandwidth usage, and thus reduce replication overhead. The experimental results show that the optimized Ceph messenger outperforms the original messenger implementation up to 40% in random writes with 4K messages. Moreover, Ceph with optimized communication subsystem shows up to 13% performance improvement as compared to original Ceph.
Céline Poilly - One of the best experts on this subject based on the ideXlab platform.
-
Employment, hours and the welfare effects of intra-firm bargaining
2020Co-Authors: Maarten Dossche, Vivien Lewis, Céline PoillyAbstract:Bilateral bargaining between a Multiple-Worker firm and individual employees leads to overhiring. With a concave production function, the firm can reduce the marginal product by hiring an additional Worker, thereby reducing the bargaining wage paid to all existing employees. We show that this externality is amplified when firms can adjust hours per Worker as well as employment. Firms keep down Workers' wage demands by reducing the number of hours per Worker and the resulting labor disutility. Our finding is particularly relevant for European economies where hours adjustment plays an important role.
-
Employment, Hours and the Welfare Effects of Intra-Firm Bargaining
Journal of Monetary Economics, 2019Co-Authors: Maarten Dossche, Vivien Lewis, Céline PoillyAbstract:Intra-firm bargaining between a Multiple-Worker firm and an individual employee leads to overhiring. Taking advantage of the decreasing returns to scale in employment, the firm can reduce the marginal product by hiring an additional Worker, thereby reducing the bargaining wage paid to all existing employees. We show that this externality is amplified when firms can adjust hours per Worker as well as employment. Hours are too low at the steady state. This misallocation of labor leads to sizeable welfare losses. Our finding is important for economies in which hours adjustment play an important role as it does in many Euro Area countries.
-
Employment, Hours and Optimal Monetary Policy
SSRN Electronic Journal, 2014Co-Authors: Maarten Dossche, Vivien Lewis, Céline PoillyAbstract:We characterize optimal monetary policy in a New Keynesian search-and-matching model where Multiple-Worker firms satisfy demand in the short run by adjusting hours per Worker. Imperfect product market competition and search frictions reduce steady state hours per Worker below the efficient level. Bargaining results in a convex wage curve’ linking wages to hours. Since the steady-state real marginal wage is low, wages respond little to hours. As a result, firms overuse the hours margin at the expense of hiring, which makes hours too volatile. The Ramsey planner uses inflation as a instrument to dampen inefficient hours fluctuations.
