Hacker News new | past | comments | ask | show | jobs | submit login

Aren’t they comparing 4 of 5 with 4 of 4?



If so that doesn't make a great deal of sense because the alternative to a coded stripe isn't a unique unreplicated stripe, it's a replicated one. So the alternative would be to race multiple reads of all known replicas, or to hedge them.


Good point. I guess it’s really 2 out of 2 versus 4 out of 6.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: