Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Plain View
HBase, mail # user - Poor HBase map-reduce scan performance


+
Bryan Keller 2013-05-01, 04:01
+
Ted Yu 2013-05-01, 04:17
+
Bryan Keller 2013-05-01, 04:31
+
Ted Yu 2013-05-01, 04:56
+
Bryan Keller 2013-05-01, 05:01
+
lars hofhansl 2013-05-01, 05:01
+
Bryan Keller 2013-05-01, 06:02
+
Michael Segel 2013-05-01, 14:24
+
lars hofhansl 2013-05-01, 06:21
+
Bryan Keller 2013-05-01, 15:00
+
Bryan Keller 2013-05-02, 01:01
+
lars hofhansl 2013-05-02, 04:41
+
Bryan Keller 2013-05-02, 04:49
+
Bryan Keller 2013-05-02, 17:54
+
Nicolas Liochon 2013-05-02, 18:00
+
lars hofhansl 2013-05-03, 00:46
+
Bryan Keller 2013-05-03, 07:17
+
Bryan Keller 2013-05-03, 10:44
+
lars hofhansl 2013-05-05, 01:33
+
Bryan Keller 2013-05-08, 17:15
+
Bryan Keller 2013-05-10, 15:46
+
Sandy Pratt 2013-05-22, 20:29
+
Ted Yu 2013-05-22, 20:39
+
Sandy Pratt 2013-05-22, 22:33
+
Ted Yu 2013-05-22, 22:57
+
Bryan Keller 2013-05-23, 15:45
+
Sandy Pratt 2013-05-23, 22:42
+
Ted Yu 2013-05-23, 22:47
+
Sandy Pratt 2013-06-05, 01:11
+
Sandy Pratt 2013-06-05, 08:09
+
yonghu 2013-06-05, 14:55
+
Ted Yu 2013-06-05, 16:12
+
yonghu 2013-06-05, 18:14
+
Sandy Pratt 2013-06-05, 18:57
+
Sandy Pratt 2013-06-05, 17:58
+
lars hofhansl 2013-06-06, 01:03
+
Bryan Keller 2013-06-25, 08:56
+
lars hofhansl 2013-06-28, 17:56
+
Bryan Keller 2013-07-01, 04:23
+
Ted Yu 2013-07-01, 04:32
+
lars hofhansl 2013-07-01, 10:59
+
Enis Söztutar 2013-07-01, 21:23
+
Bryan Keller 2013-07-01, 21:35
+
lars hofhansl 2013-05-25, 05:50
+
Enis Söztutar 2013-05-29, 20:29
+
Bryan Keller 2013-06-04, 17:01
+
Michael Segel 2013-05-06, 03:09
+
Matt Corgan 2013-05-01, 06:52
Copy link to this message
-
Re: Poor HBase map-reduce scan performance
Jean-Marc Spaggiari 2013-05-01, 10:56
@Lars, how have your calculated the 35K/row size? I'm not able to find the
same number.

@Bryan, Matt's idea below is good. With the hadoop test you always had data
locality. Which your HBase test, maybe not. Can you take a look at the JMX
console and tell us your locality % ? Also, over those 45 minutes, have you
monitored the CPWIO, GC activities, etc. to see if any of those might have
impacted the performances?

JM

2013/5/1 Matt Corgan <[EMAIL PROTECTED]>

> Not that it's a long-term solution, but try major-compacting before running
> the benchmark.  If the LSM tree is CPU bound in merging HFiles/KeyValues
> through the PriorityQueue, then reducing to a single file per region should
> help.  The merging of HFiles during a scan is not heavily optimized yet.
>
>
> On Tue, Apr 30, 2013 at 11:21 PM, lars hofhansl <[EMAIL PROTECTED]> wrote:
>
> > If you can, try 0.94.4+; it should significantly reduce the amount of
> > bytes copied around in RAM during scanning, especially if you have wide
> > rows and/or large key portions. That in turns makes scans scale better
> > across cores, since RAM is shared resource between cores (much like
> disk).
> >
> >
> > It's not hard to build the latest HBase against Cloudera's version of
> > Hadoop. I can send along a simple patch to pom.xml to do that.
> >
> > -- Lars
> >
> >
> >
> > ________________________________
> >  From: Bryan Keller <[EMAIL PROTECTED]>
> > To: [EMAIL PROTECTED]
> > Sent: Tuesday, April 30, 2013 11:02 PM
> > Subject: Re: Poor HBase map-reduce scan performance
> >
> >
> > The table has hashed keys so rows are evenly distributed amongst the
> > regionservers, and load on each regionserver is pretty much the same. I
> > also have per-table balancing turned on. I get mostly data local mappers
> > with only a few rack local (maybe 10 of the 250 mappers).
> >
> > Currently the table is a wide table schema, with lists of data structures
> > stored as columns with column prefixes grouping the data structures (e.g.
> > 1_name, 1_address, 1_city, 2_name, 2_address, 2_city). I was thinking of
> > moving those data structures to protobuf which would cut down on the
> number
> > of columns. The downside is I can't filter on one value with that, but it
> > is a tradeoff I would make for performance. I was also considering
> > restructuring the table into a tall table.
> >
> > Something interesting is that my old regionserver machines had five 15k
> > SCSI drives instead of 2 SSDs, and performance was about the same. Also,
> my
> > old network was 1gbit, now it is 10gbit. So neither network nor disk I/O
> > appear to be the bottleneck. The CPU is rather high for the regionserver
> so
> > it seems like the best candidate to investigate. I will try profiling it
> > tomorrow and will report back. I may revisit compression on vs off since
> > that is adding load to the CPU.
> >
> > I'll also come up with a sample program that generates data similar to my
> > table.
> >
> >
> > On Apr 30, 2013, at 10:01 PM, lars hofhansl <[EMAIL PROTECTED]> wrote:
> >
> > > Your average row is 35k so scanner caching would not make a huge
> > difference, although I would have expected some improvements by setting
> it
> > to 10 or 50 since you have a wide 10ge pipe.
> > >
> > > I assume your table is split sufficiently to touch all RegionServer...
> > Do you see the same load/IO on all region servers?
> > >
> > > A bunch of scan improvements went into HBase since 0.94.2.
> > > I blogged about some of these changes here:
> > http://hadoop-hbase.blogspot.com/2012/12/hbase-profiling.html
> > >
> > > In your case - since you have many columns, each of which carry the
> > rowkey - you might benefit a lot from HBASE-7279.
> > >
> > > In the end HBase *is* slower than straight HDFS for full scans. How
> > could it not be?
> > > So I would start by looking at HDFS first. Make sure Nagle's is
> disbaled
> > in both HBase and HDFS.
> > >
> > > And lastly SSDs are somewhat new territory for HBase. Maybe Andy
> Purtell
+
Bryan Keller 2013-05-01, 16:39
+
Naidu MS 2013-05-01, 07:25
+
ramkrishna vasudevan 2013-05-01, 07:27
+
ramkrishna vasudevan 2013-05-01, 07:29