A model of checkpoint behavior for applications that have I/O

Due to the increase and complexity of computer systems, reducing the overhead of fault tolerance techniques has become important in recent years. One technique in fault tolerance is checkpointing, which saves a snapshot with the information that has been computed up to a specific moment, suspending the execution of the application, consuming I/O resources and network bandwidth. Characterizing the files that are generated when performing the checkpoint of a parallel application is useful to determine the resources consumed and their impact on the I/O system. It is also important to characterize the application that performs checkpoints, and one of these characteristics is whether the application does I/O. In this paper, we present a model of checkpoint behavior for parallel applications that performs I/O; this depends on the application and on other factors such as the number of processes, the mapping of processes and the type of I/O used. These characteristics will also influence scalability, the resources consumed and their impact on the IO system. Our model describes the behavior of the checkpoint size based on the characteristics of the system and the type (or model) of I/O used, such as the number I/O aggregator processes, the buffering size utilized by the two-phase I/O optimization technique and components of collective file I/O operations. The BT benchmark and FLASH I/O are analyzed under different configurations of aggregator processes and buffer size to explain our approach. The model can be useful when selecting what type of checkpoint configuration is more appropriate according to the applications’ characteristics and resources available. Thus, the user will be able to know how much storage space the checkpoint consumes and how much the application consumes, in order to establish policies that help improve the distribution of resources.

     

Determination vitamin A source foods by pregnant women,using a simplified dietary assessment (SDA)

The International Vitamin A Consultative Group (IVACG) developed a research instrument based on consumption of vitamin-A food sources to classify populations into groups of high, moderate and low deficiency risk in the consumption of this nutrient. The instrument was tested on a population of 91 pregnant women who attended prenatal health care service run by School of Public Health of the University of S?o Paulo. Such instrument was termed Simplified Dietary Assessment (SDA) and it is comprised of a 24-hour dietary recall--Consumption Index (CI) and consumption frequency questionnaire--Usual Food Pattern (UFP). SDA pointed out the most consumed daily and weekly foods as being milk in liquid form, tomato, lettuce, margarine and banana. All these food sources belong to groups of low and moderate vitamin A content. Assignment in risk groups was based on the recommended dietary intake proposed by the Food and Agriculture Organization of the United Nations--(FAO/OMS--1991) and two-thirds of the recommended intake was considered the cutting off point. According to data obtained by the SDA, more than 50% of the population interviewed was assigned to the High and Moderate risk groups for deficiency in vitamin A intake. Statistical analysis of the data revealed a significant statistical correlation r = 0.50 (p > 0.005) and a weighted Kappa value of (kw = 0.207), which suggests that the SDA is a useful instrument and is a reasonable means for risk assignment of vitamin A deficiency among groups with inadequate levels of intake of foods as sources of this nutrient. However, the results suggest that in order to evaluate vitamin A intake appropriately, a larger number of applications of the IC questionnaires would be required.     

Analysis of parallel application checkpoint storage for system configuration

The Journal of Supercomputing - The use of fault tolerance strategies such as checkpoints is essential to maintain the availability of systems and their applications in high-performance computing...     

Correction to: A model of checkpoint behavior for applications that have I/O

The Journal of Supercomputing -