What to consider for applying backfilling on non-dedicated environments

The resource utilization level in open laboratories of several universities has been shown to be very low. Our aim is to take advantage of those idle resources for parallel computation without disturbing the local load. In order to provide a system that lets us execute parallel applications in such a non-dedicated cluster, we use an integral scheduling system that considers both Space and Time sharing concerns. For dealing with the Time Sharing (TS) aspect, we use a technique based on the communication-driven coscheduling principle. This kind of TS system has some implications on the Space Sharing (SS) system, that force us to modify the way job scheduling is traditionally done. In this paper, we analyze the relation between the TS and the SS systems in a non-dedicated cluster. As a consequence of this analysis, we propose a new technique, termed 3DBackfilling. This proposal implements the well known SS technique of backfilling, but applied to an environment with a MultiProgramming Level (MPL) of the parallel applications that is greater than one. Besides, 3DBackfilling considers the requirements of the local workload running on each node. Our proposal was evaluated in a PVM/MPI Linux cluster, and it was compared with several more traditional SS policies applied to non-dedicated environments.

CISNE-P: a global scheduling oriented to NOW environments

In this work, we present an integral scheduling system for non-dedicated clusters, termed CISNE-P, which ensures the performance required by the local applications, while simultaneously allocating cluster resources to parallel jobs. Our approach solves the problem efficiently by using a social contract technique. This kind of technique is based on reserving computational resources, preserving a predetermined response time to local users. CISNE-P is a middleware which includes both a previously developed space-sharing job scheduler and a dynamic coscheduling system, a time sharing scheduling component. The experimentation performed in a Linux cluster shows that these two scheduler components are complementary and a good coordination improves global performance significantly. We also compare two different CISNE-P implementations: one developed inside the kernel, and the other entirely implemented in the user space.

Pontages veineux in situ. Indications, technique et résultats. A propos d'une étude prospective de 26 cas consécutifs [In situ venous grafts. Indications, technique and results. Prospective study of 26 consecutive cases].

The in situ saphenous vein bypass has been introduced in our department since 1989. A total of 26 bypasses in 22 patients have been followed prospectively. Indications for revascularisation have been severe arterial insufficiency in 73% of the cases (stage III or IV). With the exception of one postoperative death (myocardial infarction), all the patients have recovered uneventfully, with a regression to stage I. No amputation has been necessary. Morbidity has been 30%, with mainly minor local complications. The primary patency rate is 83% at one year and 78% after 2 and 3 years, whereas the secondary patency rate is 91% at one year, and remains constant thereafter up to 3 years. Considering our results and those from the literature, we believe that the in situ technique is very valuable, especially for below-knee vascular reconstruction. Technical difficulties of the method are analysed.

Determination of the complexing capacity of synthetic and real wine for Zn using Absence of Gradients and Nerstian Equilibrium Stripping technique

The complexing capacity of synthetic (0.011 M tartrate in 13.5% ethanol) and real wine (Raimat Abadia) in titrations with added total Zn concentrations up to 0.03 M has been determined following the free Zn concentrations with AGNES (absence of gradients and Nernstian equilibrium stripping) technique. A correction to find the preconcentration factor or gain (Y1) really applied at each one of the ionic strengths reached due to Zn additions along the titration has been applied. The standard implementation of AGNES to real wine led to the observation of two anomalous behaviors: (a) an increasingly negative current in the deposition stage (labeled as “HER” effect) and (b) a minimum in the currents of the stripping stage plot (labeled as the “dip” effect). A practical strategy to apply AGNES avoiding the dip effect has been developed to quantify properly free Zn concentrations. The van den Berg–Ružic–Lee linearization method (assuming the existence of just 1:1 complexes) has been adapted to consider the dilution effect and the ionic strength changes. Aggregated stability constants and total ligand concentrations have been calculated from synthetic and wine titration data. The found complexing capacity in the studied wine (cT,L = 0.0179 ± 0.0007 M) indicates the contribution of ligands other than tartrate (which is confirmed to be the main one).