cassandra-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Benedict (JIRA)" <>
Subject [jira] [Commented] (CASSANDRA-6271) Replace SnapTree in AtomicSortedColumns
Date Wed, 01 Jan 2014 22:57:50 GMT


Benedict commented on CASSANDRA-6271:

That's exactly what will happen. Note that if we aren't already in the root\* then when we
ascend we will infact increment the pointer and exit if we aren't at the end.

Specifically, in this case, we would execute:
        while(!isRoot())                True
          pop()                         now on [18,24,29,32]
          i = currentIndex() + 1        i = 4
          node = currentNode();
          if (i < getKeyEnd(node))      getKeyEnd(node) == 4 => False
        while(!isRoot())                True
          pop()                         now on [8,14,37,52]
          i = currentIndex() + 1        i = 3
          node = currentNode();
          if (i < getKeyEnd(node))      getKeyEnd(node) == 4 => True

\*if we are, we must be at the end, so we're done anyway

> Replace SnapTree in AtomicSortedColumns
> ---------------------------------------
>                 Key: CASSANDRA-6271
>                 URL:
>             Project: Cassandra
>          Issue Type: Improvement
>            Reporter: Benedict
>            Assignee: Benedict
>              Labels: performance
>         Attachments: oprate.svg
> On the write path a huge percentage of time is spent in GC (>50% in my tests, if accounting
for slow down due to parallel marking). SnapTrees are both GC unfriendly due to their structure
and also very expensive to keep around - each column name in AtomicSortedColumns uses >
100 bytes on average (excluding the actual ByteBuffer).
> I suggest using a sorted array; changes are supplied at-once, as opposed to one at a
time, and if < 10% of the keys in the array change (and data equal to < 10% of the size
of the key array) we simply overlay a new array of changes only over the top. Otherwise we
rewrite the array. This method should ensure much less GC overhead, and also save approximately
80% of the current memory overhead.
> TreeMap is similarly difficult object for the GC, and a related task might be to remove
it where not strictly necessary, even though we don't keep them hanging around for long. TreeMapBackedSortedColumns,
for instance, seems to be used in a lot of places where we could simply sort the columns.

This message was sent by Atlassian JIRA

View raw message