[
https://issues.apache.org/jira/browse/CASSANDRA-7282?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14132885#comment-14132885
]
Branimir Lambov commented on CASSANDRA-7282:
--------------------------------------------
I have a question about the implementation:
You state in the preface of the NBHOM that the following condition must be
satisfied "for two keys k1, k2: k1 < k2 => k1.hashCode() < k2.hashCode()". I
can see that if the condition is satisfied the structure will work very well,
but this condition is much too strong. On one hand, I don't believe the
inequality on the right side of the condition should be strict, because this
forbids all collisions in the hash function in a totally ordered key set. More
importantly, even with <= on the right, I don't think the condition is
satisfiable for any usable hash function and in particular, I don't see how the
Murmur3 partitioner tokens satisfy it.
Could you elaborate on why this condition is satisfied by the proposed code?
> Faster Memtable map
> -------------------
>
> Key: CASSANDRA-7282
> URL: https://issues.apache.org/jira/browse/CASSANDRA-7282
> Project: Cassandra
> Issue Type: Improvement
> Components: Core
> Reporter: Benedict
> Assignee: Benedict
> Labels: performance
> Fix For: 3.0
>
> Attachments: profile.yaml, reads.svg, run1.svg, writes.svg
>
>
> Currently we maintain a ConcurrentSkipLastMap of DecoratedKey -> Partition in
> our memtables. Maintaining this is an O(lg(n)) operation; since the vast
> majority of users use a hash partitioner, it occurs to me we could maintain a
> hybrid ordered list / hash map. The list would impose the normal order on the
> collection, but a hash index would live alongside as part of the same data
> structure, simply mapping into the list and permitting O(1) lookups and
> inserts.
> I've chosen to implement this initial version as a linked-list node per item,
> but we can optimise this in future by storing fatter nodes that permit a
> cache-line's worth of hashes to be checked at once, further reducing the
> constant factor costs for lookups.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
