We consider the problem of stragglers in distributed computing systems. Stragglers, which are compute nodes that unpredictably slow down, often increase the completion times of tasks. One common approach to mitigating stragglers is work replication, where only the first completion among replicated tasks is accepted, discarding the others. However, discarding work leads to resource wastage. In this article, we propose a method for exploiting the work completed by stragglers rather than discarding it. The idea is to increase the granularity of the assigned work, and to increase the frequency of worker updates. We show that the proposed method reduces the completion time of tasks via experiments performed on a simulated cluster as well as on Amazon EC2 with Apache Hadoop.

Modern Information and Communication Technologies (ICTs) support job searches, resume creation, career development, and professional self-presentation. However, these technological tools are often tailored to high-income, highly educated users and white-collar professionals. It is unclear what interventions address the needs of job seekers who have limited resources or education, or who may be underserved in other ways. We gathered insights from the literature and generated ten tangible design concepts to address the needs of underserved job seekers. We then conducted a needs validation and speed dating study to understand which concepts were most viable among our population. We found that the three most preferred concepts immediately addressed job seekers' social and personal needs, where addressing social needs meant mediating job seekers' connections to others and supporting our job seekers' limited access to strong ties.