An online data access prediction and optimization approach for distributed systems

Current scientific applications have been producing large amounts of data. The processing, handling and analysis of such data require large-scale computing infrastructures such as clusters and grids. In this area, studies aim at improving the performance of data-intensive applications by optimizing data accesses. In order to achieve this goal, distributed storage systems have been considering techniques of data replication, migration, distribution, and access parallelism. However, the main drawback of those studies is that they do not take into account application behavior to perform data access optimization. This limitation motivated this paper which applies strategies to support the online prediction of application behavior in order to optimize data access operations on distributed systems, without requiring any information on past executions. In order to accomplish such a goal, this approach organizes application behaviors as time series and, then, analyzes and classifies those series according to their properties. By knowing properties, the approach selects modeling techniques to represent series and perform predictions, which are, later on, used to optimize data access operations. This new approach was implemented and evaluated using the OptorSim simulator, sponsored by the LHC-CERN project and widely employed by the scientific community. Experiments confirm this new approach reduces application execution time in about 50 percent, specially when handling large amounts of data.

Chk1 phosphorylation of Metnase enhances DNA repair but inhibits replication fork restart

Chk1 both arrests replication forks and enhances repair of DNA damage by phosphorylating downstream effectors. Although there has been a concerted effort to identify effectors of Chk1 activity, underlying mechanisms of effector action are still being identified. Metnase (also called SETMAR) is a SET and transposase domain protein that promotes both DNA double-strand break (DSB) repair and restart of stalled replication forks. In this study, we show that Metnase is phosphorylated only on Ser495 (S495) in vivo in response to DNA damage by ionizing radiation. Chk1 is the major mediator of this phosphorylation event. We had previously shown that wild-type (wt) Metnase associates with chromatin near DSBs and methylates histone H3 Lys36. Here we show that a Ser495Ala (S495A) Metnase mutant, which is not phosphorylated by Chk1, is defective in DSB-induced chromatin association. The S495A mutant also fails to enhance repair of an induced DSB when compared with wt Metnase. Interestingly, the S495A mutant demonstrated increased restart of stalled replication forks compared with wt Metnase. Thus, phosphorylation of Metnase S495 differentiates between these two functions, enhancing DSB repair and repressing replication fork restart. In summary, these data lend insight into the mechanism by which Chk1 enhances repair of DNA damage while at the same time repressing stalled replication fork restart. Oncogene (2012) 31, 4245-4254; doi:10.1038/onc.2011.586; published online 9 January 2012