Hi Ted,
I iostat my region server and it seems that there is an imbalance in the read
requests of the disks.
Device:tpsMB_read/sMB_wrtn/sMB_readMB_wrtn
xvdap10.40 0.00 0.00 0 0
xvdb429.0011.65
Hi Ted,
For some reason, when I try the forked version of YCSB, I can't seem to launch
more than 10 threads. I start getting the following errors:
11/06/02 02:17:35 INFO zookeeper.ZooKeeper: Initiating client connection,
connectString=xx:2181 sessionTimeout=18 watcher=hconnection
Zookeeper has an internal limit on number of connections.
Which version of hbase are you running?
On Wed, Jun 1, 2011 at 11:20 PM, Harold Lim rold...@yahoo.com wrote:
Hi Ted,
For some reason, when I try the forked version of YCSB, I can't seem to
launch more than 10 threads. I start getting
I'm running HBase 0.90.2.
-Harold
--- On Thu, 6/2/11, Ted Dunning tdunn...@maprtech.com wrote:
From: Ted Dunning tdunn...@maprtech.com
Subject: Re: How to improve HBase throughput with YCSB?
To: user@hbase.apache.org
Date: Thursday, June 2, 2011, 2:34 AM
Zookeeper has an internal limit on
Yeah.. there is a bug on that.
I am spacing the number right now. And I have to run.
On Wed, Jun 1, 2011 at 11:42 PM, Harold Lim rold...@yahoo.com wrote:
I'm running HBase 0.90.2.
-Harold
--- On Thu, 6/2/11, Ted Dunning tdunn...@maprtech.com wrote:
From: Ted Dunning
This got fixed when I removed the 127.0.1.1 entry in /etc/hosts and moved
the entries corresponding to it to 127.0.0.1. (
http://permalink.gmane.org/gmane.comp.java.hadoop.hbase.user/18878)
hair
On Tue, May 31, 2011 at 12:43 AM, Sean Bigdatafun sean.bigdata...@gmail.com
wrote:
Hi Hari,
I am
hello guys..!!
I am a newbie in Hbase.
I am trying to setup Hbase cluster on top of my hadoop cluster.
My hadoop version is 0.20.2 and I am trying to use Hbase version 0.20.6
Are they compatible with each other ?
I am able to run Hbase on my single node..
But whenever I am trying to add my
I have finally been able to spend enough time to digest/test
all recommendations and get this under control. I wanted to thank Stack,
Jack Levin, and Ted Dunning for their input.
Basically our memory was being pushed to the limit and the JVM does not
like/can not handle this. We are successfully
Is there any information from this thread that we should make sure gets into the hbase book? it
seem like Wayne went through a lot of work to get good performance and it would be nice if all the
information he gleaned from the community were recorded somewhere. If it doesn't make sense to put
It looks like you are managing zk yourself? Default is that zk only
allows 10 connections. Up it to 1000 for now. Its maxClientCnxns.
St.Ack
On Wed, Jun 1, 2011 at 11:42 PM, Harold Lim rold...@yahoo.com wrote:
I'm running HBase 0.90.2.
-Harold
--- On Thu, 6/2/11, Ted Dunning
Don't use HBase 0.20.6. Use the current release (0.90.3)
Did you configure hbase for distributed operation? What command are you using
to start the region server? Are you manually starting region servers
individually, or are you running the start-hbase.sh command from your hbase
master
So you mean to say that hadoop 0.20.6 is older version ???
Does it not work well with hadoop 0.20.2 ??
On Thu, Jun 2, 2011 at 9:04 PM, Buttler, David buttl...@llnl.gov wrote:
Don't use HBase 0.20.6. Use the current release (0.90.3)
Did you configure hbase for distributed operation? What
No. Read the manual: http://hbase.apache.org/book/notsoquick.html
St.Ack
On Thu, Jun 2, 2011 at 8:38 AM, praveenesh kumar praveen...@gmail.com wrote:
So you mean to say that hadoop 0.20.6 is older version ???
Does it not work well with hadoop 0.20.2 ??
On Thu, Jun 2, 2011 at 9:04 PM,
I'd be particularly interested how you guys came to the conclusion for
increasing block size and how you arrived at the size you chose. For
example, what metrics were you looking at that indicated the block
size was too small and what tests did you run to arrive at 256k for
the correct size?
Thanks for writing back to the list Wayne. Hopefully this message
hits you before the next CMF does. Would you mind pasting your final
JVM args and any other configs you think one of us could use writing
up your war story for the 'book' as per Jeff Whiting's suggestion?
Good stuff,
St.Ack
On
Our storefileindex was pushing 3g. We used the hfile tool to see that we had
very large keys (50-70 bytes) and small values (5-7 bytes). Jack pointed me
to a great Jira about this: https://issues.apache.org/jira/browse/HBASE-3551
.
We HAD to increase from the default and we picked 256k to reduce
I'm getting a lot of this on the slave that is doing the latest adds:
2011-06-02 00:33:05,231 WARN org.apache.hadoop.hbase.regionserver.MemStoreFlushe
r: Region urlhashv4,7F8537883DDF5230B10AA2CB13182505,1306992752074.71ab4c4527ce7
6d777f78943a86009d2. has too many store files; delaying flush up
Also, notice the output of my copy, where its now stuck on the final line.
first column is number of rows, second column is key value:
total:90460 7FECD7A2D11FFD850FDC7CA899CA3138
total:90470 7FF0787C8EC28FF760BF0E38BB1F95C8
total:90480 7FF418DDFCB134EFA7F1304762EA4A20
I just installed HBase-0.90.3 with Hadoop-0.20.203.0 and I get some sort of
zookeeper hiccup followed by an End Of File error. Any suggestions on what I
am doing wrong?
Alan
MASTER LOG FILE
Thu Jun 2 10:29:25 EDT 2011 Starting master on hadoop1
ulimit -n 1024
2011-06-02 10:29:26,218 INFO
The zk stuff is ok, it's just that hadoop1 doesn't have a zk server
but hadoop2 does (so review your configuration).
You need to replace the hadoop jar since right now you have
/hadoop-core-0.20-append-r1056497.jar
Like the doc says http://hbase.apache.org/book.html#hadoop
It is critical that
Hi St.Ack,
In my setup, Zk is being managed by HBase. I'll try increasing maxClientCnxns.
Thanks,
Harold
--- On Thu, 6/2/11, Stack st...@duboce.net wrote:
From: Stack st...@duboce.net
Subject: Re: How to improve HBase throughput with YCSB?
To: user@hbase.apache.org
Date: Thursday, June
JVM w/ 10g Heap settings below. Once we are bored with stability we will
try to up the 65 to 70 which seems to be standard.
-XX:+UseCMSInitiatingOccupancyOnly -XX:CMSInitiatingOccupancyFraction=65
-XX:+CMSParallelRemarkEnabled -XX:+UseConcMarkSweepGC -XX:NewSize=128m
-XX:MaxNewSize=128m
Ok, I think I know why it gets stuck there. That's where the hole is in the
original table. I skipped past the hole and it is off and running again.
Knock on wood!
Robert
-Original Message-
From: Robert Gonzalez [mailto:robert.gonza...@maxpointinteractive.com]
Sent: Thursday, June
Here's another clue: the process is taking up lots of cpu time, likes its in
some kind of loop, but the output indicates that its stuck on the same section.
Robert
-Original Message-
From: Robert Gonzalez [mailto:robert.gonza...@maxpointinteractive.com]
Sent: Thursday, June 02, 2011
And more info. The copy dies on a regionserver failure. Here is the exception
when it dies:
2011-06-02 13:29:07,546 FATAL org.apache.hadoop.hbase.regionserver.HRegionServer
: ABORTING region server serverName=c1-s06.atxd.maxpointinteractive.com,60020,13
06860799744, load=(requests=0,
So, cluster is OK after the below crash? Regions come up fine on new
servers and .META. is fine?
Below is interesting in that we failed a split because we could not
write an edit to the .META. (how many handlers are you running with?
And what is going on on the .META. server at around this time?
First a clarification: everything is happening within the context of a single
cluster of 55 machines, there is no inter-cluster copying. I restarted c1-s06,
the regionserver that died, and by the way, all new data seems to be going to
this server first. Is there a reason for this? This is
It can't get to c1-s19. It timesout trying to connect. Can you
figure whats up w/ that? On always going to the same server, is this
a case of http://hbase.apache.org/book.html#timeseries? Or perhaps,
regions split and go elsewhere but distcp is writing from the src in
order?
St.Ack
On Thu,
Not to beat a dead horse, but I thought a bit more about the problem.
If you want to do this all in HBase using a M/R job...
Lets define the following:
SELECT *
FROM A, B
WHERE A.a = B.a
AND A.b = B.b
AND A.c = xxx
AND A.d = yyy
AND B.e = zzz
Is the sample query.
So our join
Is there an easy way to control this? some magic setting in the
HBAseConfiguration passed to HTable?
The problem we're facing is that for each put and get we block for however
long it takes to do the put.
The norm put/get is fast or at least impressive to me and yet some puts take
10sec +
1) You probably want to upgrade to a more recent version of HBase
2) You probably want to read this:
http://hbase.apache.org/book.html#performance
Not knowing anything about your cluster size or table design, Put delays can be
exacerbated by a number of things.
3) As for the time limit, I
I was reading through the HBase book and came across the following in *6.2. On
the number of column families.http://hbase.apache.org/book.html#number.of.cfs
*
*
*
*HBase currently does not do well with anything about two or three column
families so keep the number of column families in your
On Thu, Jun 2, 2011 at 2:40 PM, Leif Wickland leifwickl...@gmail.com wrote:
Do you think I should look for ways to reduce the number of CFs?
If you can, yes (The book is current -- the work on making hbase do
better with more CFs is yet to be done).
Good luck,
St.Ack
Is there a JIRA for issuing flushes and compactions on a per column family
basis?
On 6/2/11 2:48 PM, Stack st...@duboce.net wrote:
On Thu, Jun 2, 2011 at 2:40 PM, Leif Wickland leifwickl...@gmail.com wrote:
Do you think I should look for ways to reduce the number of CFs?
If you can, yes
https://issues.apache.org/jira/browse/HBASE-3149 for flushes, not sure
about compactions.
J-D
On Thu, Jun 2, 2011 at 2:57 PM, Vidhyashankar Venkataraman
vidhy...@yahoo-inc.com wrote:
Is there a JIRA for issuing flushes and compactions on a per column family
basis?
On 6/2/11 2:48 PM, Stack
Re: Is that still considered current? Do folks on the list generally agree
with that guideline?
Yes and yes. HBase runs better with fewer CFs.
-Original Message-
From: Leif Wickland [mailto:leifwickl...@gmail.com]
Sent: Thursday, June 02, 2011 5:41 PM
To: user@hbase.apache.org
Hi,
I am not able to find information regarding the algorithm that decides which
region a particular row belongs to in an HBase cluster. Does the algorithm
take into account the number of physical nodes ? Where can I find more
details about it ?
I went through the HBase book and the OpenTSDB
Hi
I want to build a hbase cluster in the production environment. Which
version of hbase and hadoop is recommended? The apache or the cdh3? Is cdh3
a open source version? In some artical, it says if the two version is not
matched, hbase well lose data!
thx
Peng
Dear all,
I want to design Follower schema like Twitter. I have 2 design
Design 1:
userId{//rowkey
followerId: time,
}
Design 2 :
[userId][followerId]{//rowkey
time: time
}
I have 2 question:
1. Does HBase support scan data of rowkey by column?
2. Which design is better? I think that
It seems that HTable atomic operations (e.g., checkAndPut and
checkAndDelete) are not supported by the current REST implementation. The
RemoteHTable class throws an IOException when these methods are called. Is
there any reason why these operations are unsupported in REST? Are any plans
to support
Hello guys.
I just have installed hbase on my hadoop cluster.
HMaster,HRegionServer,HQuorum Peer all are working fine.. as I can see these
processes running through JPS.
Is there any way to know which regionservers are running right and not ?
I mean is there some kind of hbase web UI or anyway
See http://hbase.apache.org/book/book.html
Let us know if there are holes in the setup it so we can plug them.
St.Ack
On Thu, Jun 2, 2011 at 10:12 PM, praveenesh kumar praveen...@gmail.com wrote:
Hello guys.
I just have installed hbase on my hadoop cluster.
HMaster,HRegionServer,HQuorum
I have 2 question:
1. Does HBase support scan data of rowkey by column?
You mean secondary indexes? No:
http://hbase.apache.org/book.html#secondary.indices
2. Which design is better? I think that design 2 is better when user have
large amount of follower.
I cover a bunch of designs in this
This is discussed in the book: http://hbase.apache.org/book.html#hadoop
J-D
On Thu, Jun 2, 2011 at 6:09 PM, 吕鹏 lvpengd...@gmail.com wrote:
Hi
I want to build a hbase cluster in the production environment. Which
version of hbase and hadoop is recommended? The apache or the cdh3? Is cdh3
a
2011/6/2 praveenesh kumar praveen...@gmail.com
Hello guys.
I just have installed hbase on my hadoop cluster.
HMaster,HRegionServer,HQuorum Peer all are working fine.. as I can see
these
processes running through JPS.
Is there any way to know which regionservers are running right and not ?
45 matches
Mail list logo