Search for: All records

One Health initiatives have advanced zoonotic disease management by recognizing the interconnectedness of three sectors of governance (human, ecosystem, and animal) and by identifying options that can improve full‐system health. Although One Health has had many successes, its full realization may be inhibited by a lack of strategies to overcome simultaneous impediments in decision making and governance. Decision impediments that hinder management may include uncertainty, risk, resource limitations, and trade‐offs among objectives. Governance impediments arise from disparities in costs and benefits of disease management among sectors. Tools and strategies developed from decision science, collaboration, and negotiation theory can help articulate and overcome coinciding decision and governance impediments and enhance multisectoral One Health initiatives. In cases where collaboration and negotiation are insufficient to address disparities in cross‐sector costs and benefits, altering incentive structures might improve disease‐specific outcomes and improve the realization of One Health. 

To advance understanding of doctoral student experiences and the high attrition rates among Science, Technology, Engineering, and Mathematics (STEM) doctoral students, we developed and examined the psychological profiles of different types of doctoral students. We used latent class analysis on self-reported psychological data relevant to psychological threat from 1,081 incoming doctoral students across three universities and found that the best-fitting model delineated four threat classes: Lowest Threat , Nonchalant , Engaged/Worried , and Highest Threat . These classes were associated with characteristics measured at the beginning of students’ first semester of graduate school that may influence attrition risk, including differences in academic preparation (e.g., amount of research experience), self-evaluations and perceived fit (e.g., sense of belonging), attitudes towards graduate school and academia (e.g., strength of motivation), and interpersonal relations (e.g., perceived social support). Lowest Threat students tended to report the most positive characteristics and Highest Threat students the most negative characteristics, whereas the results for Nonchalant and Engaged/Worried students were more mixed. Ultimately, we suggest that Engaged/Worried and Highest Threat students are at relatively high risk of attrition. Moreover, the demographic distributions of profiles differed, with members of groups more likely to face social identity threat (e.g., women) being overrepresented in a higher threat profile (i.e., Engaged/Worried students) and underrepresented in lower threat profiles (i.e., Lowest Threat and Nonchalant students). We conclude that doctoral students meaningfully vary in their psychological threat at the beginning of graduate study and suggest that these differences may portend divergent outcomes. 

Large-scale parallel file systems (PFSs) play an essential role in high-performance computing (HPC). However, despite their importance, their reliability is much less studied or understood compared with that of local storage systems or cloud storage systems. Recent failure incidents at real HPC centers have exposed the latent defects in PFS clusters as well as the urgent need for a systematic analysis. To address the challenge, we perform a study of the failure recovery and logging mechanisms of PFSs in this article. First, to trigger the failure recovery and logging operations of the target PFS, we introduce a black-box fault injection tool called   PFault , which is transparent to PFSs and easy to deploy in practice.   PFault emulates the failure state of individual storage nodes in the PFS based on a set of pre-defined fault models and enables examining the PFS behavior under fault systematically. Next, we apply PFault to study two widely used PFSs: Lustre and BeeGFS. Our analysis reveals the unique failure recovery and logging patterns of the target PFSs and identifies multiple cases where the PFSs are imperfect in terms of failure handling. For example, Lustre includes a recovery component called LFSCK to detect and fix PFS-level inconsistencies, but we find that LFSCK itself may hang or trigger kernel panics when scanning a corrupted Lustre. Even after the recovery attempt of LFSCK, the subsequent workloads applied to Lustre may still behave abnormally (e.g., hang or report I/O errors). Similar issues have also been observed in BeeGFS and its recovery component BeeGFS-FSCK. We analyze the root causes of the abnormal symptoms observed in depth, which has led to a new patch set to be merged into the coming Lustre release. In addition, we characterize the extensive logs generated in the experiments in detail and identify the unique patterns and limitations of PFSs in terms of failure logging. We hope this study and the resulting tool and dataset can facilitate follow-up research in the communities and help improve PFSs for reliable high-performance computing.