Memory accounting without partitions

Abstract

Operating systems account for memory consumption and allow for termination at the level of individual processes. As a result, if one process consumes too much memory, it can be terminated without damaging the rest of the system. This same capability can be useful within a single application that encompasses subtasks. An individual task may go wrong either because the task's code is untrusted or because the task's input is untrusted. Conventional accounting mechanisms, however, needlessly complicate communication among tasks by partitioning their object spaces. In this paper, we show how to provide applications with per-task memory accounting without per-task object partitions.