Why not align the node to 64 bytes? #96
Bilibotter
started this conversation in
General
Replies: 1 comment
-
Hi, that's because when interacting with various nodes, there will be no False Sharing (only pointers to them are stored in buckets). On the other hand, it is possible in buckets. For example, if you increase the number of nodes in each bucket. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I've been reading the source code of Otter lately, and it's amazing.
I read the CLHT paper.In my understanding, it should align the node to 64 bytes.
But I found that it only aligns the bucket to 64 bytes, not the node.
There may be an error in my understanding, so I'm wondering about the reason for only aligning the bucket to 64 bytes.
Beta Was this translation helpful? Give feedback.
All reactions