Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ec109685
11 months ago
|
parent
|
context
|
favorite
| on:
Erasure Coding versus Tail Latency
Aren’t they comparing 4 of 5 with 4 of 4?
jeffbee
11 months ago
[–]
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.
ec109685
11 months ago
|
parent
[–]
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: