When building storage systems that aim to simultaneously provide robustness, scalability, and efficiency, one faces a fundamental tension, as higher robustness typically incurs higher costs and thus hurts both efficiency and scalability. My research shows that an approach to storage system design based on a simple principle—separating data from metadata—can yield systems that address elegantly and effectively that tension in a variety of settings. One observation motivates our approach: much of the cost paid by many strong protection techniques is incurred to detect errors. This observation suggests an opportunity: if we can build a low-cost oracle to detect errors and identify correct data, it may be possible to reduce the cost of protection without weakening its guarantees. This dissertation shows that metadata, if carefully designed, can serve as such an oracle and help a storage system protect its data with minimal cost. This dissertation shows how to effectively apply this idea in three very different systems: Gnothi—a storage replication protocol that combines the high availability of asynchronous replication and the low cost of synchronous replication for a small-scale block storage; Salus—a large-scale block storage with unprecedented guarantees in terms of consistency, availability, and durability in the face of a wide range of server failures; and Exalt—a tool to emulate a large storage system with 100 times fewer machines. / text

We previously found that intermittent administration of 3,4-methylenedioxymethamphetamine (MDMA, “Ecstasy”) to adolescent male rats protected against the behavioral and serotonergic neurotoxic effects of a subsequent MDMA binge. Similar results have been reported for the dopamine (DA) neurotoxin methamphetamine (METH). The present study tested the hypothesis that intermittent adolescent MDMA exposure would protect against the DA neurotoxic effects of a METH binge. Male Sprague-Dawley rats were injected s.c. with MDMA (10 mg/kg x 2; 4-h interdose interval) or saline every fifth day from postnatal day (PD) 35 through PD 60. The animals were then challenged with either a low- or high-dose METH binge (4 or 8 mg/kg x 4; 2- h interdose interval) or saline on PD 67. Activity was measured 1 day after the binge, and regional serotonin transporter (SERT) and dopamine transporter (DAT) expression were analyzed at PD 74 by radioligand binding. All animals treated with METH on the challenge day became hyperthermic, independent of pretreatment conditions. Both MDMA-pretreated and drug-naïve rats also showed a dose-dependent hypoactivity 24 h after the first dose of the METH binge. The SERT binding results indicated that adolescent pretreatment with MDMA provided full or partial protection (depending on the brain region) against the serotonergic deficits produced by METH in previously drug-naïve animals. In contrast, MDMA pretreatment failed to protect against METH-induced decreases in striatal DAT binding. These results suggest that the neuroprotective 2 effects of adolescent MDMA pretreatment are confined to the serotonergic system, possibly reflecting a selective upregulation of antioxidant mechanisms in that system.