
The PASIS read/write protocol implements a Byzantine fault-tolerant erasure-coded atomic register. The prototype PASIS storage system implementation provides excellent best-case performance. Writes require two round trips and contention- and failure-free reads require one. Unfortunately, even though writes and reads are wait-free in PASIS, Byzantine components can induce correct clients to perform an unbounded amount of work. In this extended abstract, we enumerate the avenues by which Byzantine servers and clients can induce correct clients to perform an unbounded amount of work in PASIS. We sketch extensions to the PASIS protocol and Lazy Verification that bound the amount of work Byzantine components can induce correct clients to perform. We believe that the extensions provide bounded wait-free reads and writes. We also believe that an implementation that incorporates these extensions will preserve the excellent best-case performance of the original PASIS prototype.
Byzantine fault-tolerant, bounded wait-free, erasure-coded storage, 004, non-skipping timestamps, ddc: ddc:004
Byzantine fault-tolerant, bounded wait-free, erasure-coded storage, 004, non-skipping timestamps, ddc: ddc:004
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
