In this work we present the architectural and performance studies concerning a prototype of a distributed Tier2 infrastructure for HEP, instantiated between the two Italian sites of INFN-Romal and ...INFN-Napoli. The network infrastructure is based on a Layer-2 geographical link, provided by the Italian NREN (GARR), directly connecting the two remote LANs of the named sites. By exploiting the possibilities offered by the new distributed file systems, a shared storage area with synchronous copy has been set up. The computing infrastructure, based on an OpenStack facility, is using a set of distributed Hypervisors installed in both sites. The main parameter to be taken into account when managing two remote sites with a single framework is the effect of the latency, due to the distance and the end-to-end service overhead. In order to understand the capabilities and limits of our setup, the impact of latency has been investigated by means of a set of stress tests, including data I/O throughput, metadata access performance evaluation and network occupancy, during the life cycle of a Virtual Machine. A set of resilience tests has also been performed, in order to verify the stability of the system on the event of hardware or software faults. The results of this work show that the reliability and robustness of the chosen architecture are effective enough to build a production system and to provide common services. This prototype can also be extended to multiple sites with small changes of the network topology, thus creating a National Network of Cloud-based distributed services, in HA over WAN.
In 2012, 14 Italian institutions participating in LHC Experiments won a grant from the Italian Ministry of Research (MIUR), with the aim of optimising analysis activities, and in general the Tier2 ...Tier3 infrastructure. We report on the activities being researched upon, on the considerable improvement in the ease of access to resources by physicists, also those with no specific computing interests. We focused on items like distributed storage federations, access to batch-like facilities, provisioning of user interfaces on demand and cloud systems. R&D on next-generation databases, distributed analysis interfaces, and new computing architectures was also carried on. The project, ending in the first months of 2016, will produce a white paper with recommendations on best practices for data-analysis support by computing centers.
In modern Data Grid infrastructures, we increasingly face the problem of providing the running applications with fast and reliable access to large data volumes, often geographically distributed ...across the network. As a direct consequence, the concept of replication has been adopted by the grid community to increase data availability and maximize job throughput. To be really effective, such process has to be driven by specific optimization strategies that define when and where replicas should be created or deleted on a per-site basis, and which replicas a job should use. These strategies have to take into account the available network bandwidth as a primary resource, prior to any consideration about storage or processing power. We present a novel replica management service, integrated within the Gluedomains active network monitoring architecture, designed and implemented within the centralized collective middleware framework of the SCoPE project to provide network-aware transfer services for data intensive Grid applications.
The large amount of data produced by the ATLAS experiment needs new computing paradigms for data processing and analysis, which involve many computing centres spread around the world. The computing ...workload is managed by regional federations, called “clouds”. The Italian cloud consists of a main (Tier-1) center, located in Bologna, four secondary (Tier-2) centers, and a few smaller (Tier-3) sites. In this contribution we describe the Italian cloud facilities and the activities of data processing, analysis, simulation and software development performed within the cloud, and we discuss the tests of the new computing technologies contributing to evolution of the ATLAS Computing Model.
ATLAS data are distributed centrally to Tier-1 and Tier-2 sites. The first stages of data selection and analysis take place mainly at Tier-2 centres, with the final, iterative and interactive, stages ...taking place mostly at Tier-3 clusters. The Italian ATLAS cloud consists of a Tier-1, four Tier-2s, and Tier-3 sites at each institute. Tier-3s that are grid-enabled are used to test code that will then be run on a larger scale at Tier-2s. All Tier-3s offer interactive data access to their users and the possibility to run PROOF. This paper describes the hardware and software infrastructure choices taken, the operational experience after 10 months of LHC data, and discusses site performances.
Muon identification (MUID) and high-momentum measurement accuracy is crucial to fully exploit the physics potential that will be accessible with the ATLAS experiment at the LHC. The muon energy of ...physics interest ranges in a large interval from few GeV, where the b-physics studies dominate the physics program, up to the highest values that could indicate the presence of new physics. The muon detection system of the ATLAS detector is characterized by two high-precision tracking systems, namely the inner detector (ID) and the muon spectrometer, (MS) plus a thick calorimeter that ensures a safe hadron absorption filtering with high-purity muons with energy above 3 GeV. In order to combine the muon tracks reconstructed in the ID and the MS, a MUID object-oriented software package has been developed. The purpose of the MUID procedure is to associate tracks found in the MS with the corresponding ID track and calorimeter information in order to identify muons at their production vertex with optimum parameter resolution. The performance of these two combined systems has been evaluated with Monte Carlo studies using single muons of fixed-transverse momentum and with full physics events.
Lenses exposed to high concentrations of xylose in organ culture produce xylitol, and they lose transparency and exhibit other changes characteristic of cataracts. Most previous studies of this model ...system for cataractogenesis have employed rat or rabbit lenses, where the activity of the enzyme aldose reductase has been definitely implicated as the initiating factor. Since lenses from this species have much higher aldose reductase activity and have other differences relative to human lenses, the relevance of these findings to the human lens is uncertain. To determine the effects of xylose on the lenses of a primate, lenses from the rhesus monkey(Macaca mulatta)were incubated 24–48 hr in control medium or in TC-199 medium containing 30 mmxylose. Xylose caused a general haziness, focal swelling of epithelial cells, and swollen peripheral fiber cells, but the changes were much less pronounced than in rat lenses under similar conditions. Monkey lenses exposed to 30 mmglucose, galactose or xylose accumulated measurable sorbitol, dulcitol or xylitol, respectively, but the amounts were much lower than in rat lenses, perhaps reflecting the lower aldose reductase and higher sorbitol dehydrogenase activities in monkey lenses. The damage to monkey lenses appeared to be limited to the outer layers. In monkey lenses, xylose caused little, if any, change in membrane transport of choline or α-aminoisobutyrate, but severely depressed synthesis of phosphorylcholine (P-choline), and increased leakage of P-choline into the culture medium, leading to a decrease in the P-choline concentration within 24–48 hr. In summary, xylose-induced damage to monkey lenses in organ culture is qualitatively similar to that seen in rat lenses, but the changes are much less rapid and severe. Culture of monkey lenses with xylose provides a model system to extend previous studies of sugar cataractogenesis in rats to a species more closely related to humans.
The means by which the two hemispheres coordinate processing of information are not well understood. By means of a tachistoscopic paradigm, we have shown repeatedly that performance is better when ...two conflicting tasks are presented to separate hemispheres than when both tasks are presented to a single hemisphere. The present study examines whether this effect is restricted to a specific range of task difficulty. Adult right-handers viewed two conflicting naming tasks by means of a tachistoscope. Task difficulty was lowered by reducing processing load (Experiment I: N = 32). Task difficulty was raised by projecting a visual mask 40 ms after offset of the visual displays (Experiment II: N = 10). At lower levels of processing load, dividing conflicting tasks between the hemispheres was beneficial, but not significantly so. At higher levels of load, and at either higher or lower loads with a visual mask, there were significant benefits associated with dividing conflicting tasks between the hemispheres. Three alternative explanations are discussed for the absence of an advantage associated with between-hemisphere division of inputs when task difficulty is reduced.
PDF
