hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Yu Li (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-14463) Severe performance downgrade when parallel reading a single key from BucketCache
Date Sun, 27 Sep 2015 17:53:05 GMT

    [ https://issues.apache.org/jira/browse/HBASE-14463?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14909817#comment-14909817
] 

Yu Li commented on HBASE-14463:
-------------------------------

Notice that in this UT case we are evicting a block every 10 *milliseconds* to demo the read/write
contention, which is the reason of the change on perf number (was 0.318s before adding the
block evict thread). But in real world there should be much less read/write contention since
BucketCache uses LRU as its eviction algorithm. I've also confirmed on my local env that increasing
the eviction period (like to 100ms) would bring a much better number (similar to 0.318s, with
some deviation in different run)

> Severe performance downgrade when parallel reading a single key from BucketCache
> --------------------------------------------------------------------------------
>
>                 Key: HBASE-14463
>                 URL: https://issues.apache.org/jira/browse/HBASE-14463
>             Project: HBase
>          Issue Type: Bug
>    Affects Versions: 0.98.14, 1.1.2
>            Reporter: Yu Li
>            Assignee: Yu Li
>             Fix For: 2.0.0, 1.2.0, 1.3.0, 1.0.3, 1.1.3, 0.98.16
>
>         Attachments: HBASE-14463.patch, HBASE-14463_v2.patch, HBASE-14463_v3.patch, HBASE-14463_v4.patch,
HBASE-14463_v5.patch, TestBucketCache-new_with_IdLock.png, TestBucketCache-new_with_IdReadWriteLock.png,
TestBucketCache_with_IdLock.png, TestBucketCache_with_IdReadWriteLock-resolveLockLeak.png,
TestBucketCache_with_IdReadWriteLock.png
>
>
> We store feature data of online items in HBase, do machine learning on these features,
and supply the outputs to our online search engine. In such scenario we will launch hundreds
of yarn workers and each worker will read all features of one item(i.e. single rowkey in HBase),
so there'll be heavy parallel reading on a single rowkey.
> We were using LruCache but start to try BucketCache recently to resolve gc issue, and
just as titled we have observed severe performance downgrade. After some analytics we found
the root cause is the lock in BucketCache#getBlock, as shown below
> {code}
>       try {
>         lockEntry = offsetLock.getLockEntry(bucketEntry.offset());
>         // ...
>         if (bucketEntry.equals(backingMap.get(key))) {
>           // ...
>           int len = bucketEntry.getLength();
>           Cacheable cachedBlock = ioEngine.read(bucketEntry.offset(), len,
>               bucketEntry.deserializerReference(this.deserialiserMap));
> {code}
> Since ioEnging.read involves array copy, it's much more time-costed than the operation
in LruCache. And since we're using synchronized in IdLock#getLockEntry, parallel read dropping
on the same bucket would be executed in serial, which causes a really bad performance.
> To resolve the problem, we propose to use ReentranceReadWriteLock in BucketCache, and
introduce a new class called IdReadWriteLock to implement it.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message