Skip to content

starting doc on dhts #28

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gvelez17 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

starting doc on dhts #28

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions TOPICS/storage-and-discovery/DHTs.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
## Decentralized Hash Tables

### Bigtable as a DHT

It is layers. There is a DHT with 64 megabyte blocks. The tabular data is in column store format in a LSM tree.
With a 2^21 fanout the blocks are never more than 3 deep. All nodes have the root. So never more then 2 network hops.
They keep the 2nd layer in ram so no more than 1 seek per block.

And since each block is amortised across the many rows in a column to reach 64 MiB compressed it is very fast at table scans.

This is very different then a ipfs dht with far less fanout and one object retrieved per DHT lookup with poor amortiseation.