accumulo-notifications mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Ben Manes (JIRA)" <>
Subject [jira] [Commented] (ACCUMULO-4626) improve cache hit rate via weak reference map
Date Thu, 04 May 2017 18:21:04 GMT


Ben Manes commented on ACCUMULO-4626:

I would guess that a distributed cache wouldn't offer many benefits, if we can assume that
data consistency is handled by the database already (since that is a fundamental need). The
replication, remote calls, etc. sound like overhead. Most of the distributed caches have slow
in-memory caches due to network and serialization being the primary bottlenecks. Perhaps integrating
Cassandra's off-heap cache would be a better / easier option, since it was extracted into
a reusable library ([ohc|]).

If caches were pluggable then a JCache adapter might be possible. Its not great standard,
but it would allow for using any implementor (most of which are open-source). [~kturner] was
pondering a pluggable layer in the TinyLFU patch.

> improve cache hit rate via weak reference map
> ---------------------------------------------
>                 Key: ACCUMULO-4626
>                 URL:
>             Project: Accumulo
>          Issue Type: Improvement
>          Components: tserver
>            Reporter: Adam Fuchs
>              Labels: performance, stability
>          Time Spent: 1h
>  Remaining Estimate: 0h
> When a single iterator tree references the same RFile blocks in different branches we
sometimes get cache misses for one iterator even though the requested block is held in memory
by another iterator. This is particularly important when using something like the IntersectingIterator
to intersect many deep copies. Instead of evicting completely, keeping evicted blocks into
a WeakReference value map can avoid re-reading blocks that are currently referenced by another
deep copied source iterator.
> We've seen this in the field for some of Sqrrl's queries against very large tablets.
The total memory usage for these queries can be equal to the size of all the iterator block
reads times the number of readahead threads times the number of files times the number of
IntersectingIterator children when cache miss rates are high. This might work out to something
> {code}
> 16 readahead threads * 200 deep copied children * 99% cache miss rate * 20 files * 252KB
per reader = ~16GB of memory
> {code}
> In most cases, evicting to a weak reference value map changes the cache miss rate from
very high to very low and has a dramatic effect on total memory usage.

This message was sent by Atlassian JIRA

View raw message