On the graceful degradation of phase-locked clocks

The use of phase-locked clocks to limit clock skews to fractions of the clock period while keeping the algorithm overhead very small is investigated. The number of clocks in the system required to ensure that up to m arbitrary failures can be tolerated with all the good clocks still in synchrony has been shown to be N>or=3m+1. It is shown here that, if N<or=3m, it is impossible to guarantee even that a small subset of the nonfaulty clocks will always be mutually synchronized, i.e., phase-locked clocks do not necessarily degrade gracefully.<<ETX>>