Availability and Utility of Idle Memory in Workstation Clusters

In this paper, we examine the availability and utility of idle memory inworkstation clusters. We attempt to answer the following questions. First,how much of the total memory in a workstation cluster can be expected to beidle? This provides an estimate of the opportunity for hosting guest data.Second, how much memory can be expected to be idle on individual workstations?This helps determine the recruitment policy -- how much memory should berecruited on individual hosts? Third, what is the distribution of memoryidle-times? This indicates how long guest data can be expected to survive;applications that access their data-sets frequently within the expectedlife-time of guest data are more likely to benefit from exploiting idlememory. Fourth, how much performance improvement can be achieved foroff-the-shelf clusters without customizing the operating system and/or theprocessor firmware? Finally, how long and how frequently might a user have towait to reclaim her machine if she volunteers to host guest pages on hermachine? This helps answer the question of social acceptability. To answerthe questions relating to the availability of idle memory, we have analyzedtwo-week long traces from two workstation pools with different sizes,locations, and patterns of use. To evaluate the expected benefits and costs,we have simulated five data-intensive applications (0.5 GB-5 GB) on theseworkstation pools.