HI Anze,
In word, yes - 0.20.4 is not that stable in my experience, and
upgrading to the latest CDH3 beta (which includes HBase 0.89.20100924)
should give you a huge improvement in stability.
You'll still need to do a bit of tuning of settings, but once it's
well tuned it should be able to hold u
Hi Anze,
Our production cluster used HBase 0.20.6 and hdfs (CDH3b2), and we work
for stability about a month. Some issue we have been met, and may helpful to
you.
HDFS:
1. hbase file has short life cycle than map-red, some times there're
many blocks should be delete, we should tuning for
HBase is not designed or well tested for production or stability on 2 nodes.
It will work on 2 nodes, but do not expect good performance or stability.
What is the hardware configuration and daemon setup on this cluster of 2 nodes?
How many cores, spindles, RAM, heap sizes etc... And you have t
related to exception handling and DFS errors. The according
HDFS releases (CDH3 or 20-append) provide true durability.
Thanks for sharing!
JG
> -Original Message-
> From: baggio liu [mailto:baggi...@gmail.com]
> Sent: Monday, December 13, 2010 8:45 AM
> To: user@hbase.apache.or
Some comments inline in the below.
On Mon, Dec 13, 2010 at 8:45 AM, baggio liu wrote:
> Hi Anze,
> Our production cluster used HBase 0.20.6 and hdfs (CDH3b2), and we work
> for stability about a month. Some issue we have been met, and may helpful to
> you.
>
Thanks for writing back to the lis
Hi,
does https://issues.apache.org/jira/browse/HBASE-3334
prevent me currently from using 0.20-append trunk with 0.90-rc1
to build or can I just replace the hadoop.jar and be done?
Christian
On Dec 13, 2010, at 6:44 PM, Stack wrote:
>>Beside upon, in production cluster, data loss is
Just replace the jar.
St.Ack
On Mon, Dec 13, 2010 at 10:45 AM, Christian van der Leeden
wrote:
> Hi,
>
> does https://issues.apache.org/jira/browse/HBASE-3334
> prevent me currently from using 0.20-append trunk with 0.90-rc1
> to build or can I just replace the hadoop.jar and be done?
>
>
We we're having no end to "buffet" of errors and stability problems with
20.3 when we ran big mapreduce jobs to insert data. Upgraded to 20.6
last week, and have not seen any instability. Just my anecdotal
experience.
-geoff
-Original Message-
From: Anze [mailto:anzen...@volja.net]
Sent:
First of all, thank you all for the answers. I appreciate it!
To recap:
- 0.20.4 is known to be "fragile"
- upgrade to 0.89 (cdh3b3) would improve stability
- GC should be monitored and system tuned if necessary (not sure how to do
that - yet :)
- memory should be at least 2GB, better 4GB+ (we
Where should i download the branch-0.20-append? I can't get the compiled
jar from url as follow:
http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.20-append .
On Tue, Dec 14, 2010 at 1:44 AM, Stack wrote:
> Some comments inline in the below.
>
> On Mon, Dec 13, 2010 at 8:45 AM, ba
Please see comment inline. :D
2010/12/14 Stack
> Some comments inline in the below.
>
> On Mon, Dec 13, 2010 at 8:45 AM, baggio liu wrote:
> > Hi Anze,
> > Our production cluster used HBase 0.20.6 and hdfs (CDH3b2), and we work
> > for stability about a month. Some issue we have been met, a
On Tue, Dec 14, 2010 at 1:46 AM, Anze wrote:
>
> First of all, thank you all for the answers. I appreciate it!
>
> To recap:
> - 0.20.4 is known to be "fragile"
Yes. It had a bug that would cause deadlock.
> - upgrade to 0.89 (cdh3b3) would improve stability
> - GC should be monitored and syst
On Tue, Dec 14, 2010 at 5:56 AM, 陈加俊 wrote:
> Where should i download the branch-0.20-append? I can't get the compiled
> jar from url as follow:
> http://svn.apache.org/viewvc/hadoop/common/branches/branch-0.20-append .
>
The link points to the svn repository. The cited doc. says you need
to b
Hi Baggio,
Sounds like you have some good experience with HDFS. Some comments inline below:
On Tue, Dec 14, 2010 at 6:47 AM, baggio liu wrote:
>
> > In fact, we found the low ivalid speed is because datanode invalid limit
> per heartbeat. Many invaild block stay in namenode, and can not dispatch
On Tue, Dec 14, 2010 at 6:47 AM, baggio liu wrote:
>> This can be true. Yes. What are you suggesting here? What should we
>> tune?
>>
>> In fact, we found the low ivalid speed is because datanode invalid limit
> per heartbeat. Many invaild block stay in namenode, and can not dispatch to
> data
Hi Todd,
Very appreciate to receive your reply :D
1. HDFS-611 can improve block invalidation rate, but it can not solve our
problem. We found the bottleneck is the number invalid block which datanode
fetched in a heartbeat. As stack say, we just make BLOCK_INVALIDATE_CHUNK
configuable, and inc
Is there a reason you are not using a recent version of 0.90?
On Mon, Mar 21, 2011 at 1:17 PM, Stuart Scott wrote:
> We are using Hbase 0.89.20100924+28, r
>
No, map-reduce is not really necessary to add so few rows.
Our internal tests repeatedly load 10-100 million rows without much fuss.
And that is on clusters ranging from 3 to 11 nodes.
On Mon, Mar 21, 2011 at 1:17 PM, Stuart Scott wrote:
> Is the only way to upload (say 1,000,000 rows) via map
This rate is dramatically slow than I would suspect. In our tests, a single
insertion program
has trouble inserting more than about 24,000 records per second, but that is
because we
are inserting kilobyte values and the network interfaces are saturated at
this point. These
tests are being done us
1 March 2011 20:20
To: user@hbase.apache.org
Cc: Stuart Scott
Subject: Re: HBase Stability
No, map-reduce is not really necessary to add so few rows.
Our internal tests repeatedly load 10-100 million rows without much
fuss. And that is on clusters ranging from 3 to 11 nodes.
On Mon, Mar 2
Cc: Stuart Scott
Subject: Re: HBase Stability
Is there a reason you are not using a recent version of 0.90?
On Mon, Mar 21, 2011 at 1:17 PM, Stuart Scott wrote:
> We are using Hbase 0.89.20100924+28, r
>
shouldn't collapse?
Regards
Stuart
-Original Message-
From: Buttler, David [mailto:buttl...@llnl.gov]
Sent: 21 March 2011 20:46
To: user@hbase.apache.org
Subject: RE: HBase Stability
Have you seen Todd Lipcon's post on MSLAB's?
http://www.cloudera.com/blog/2011/02/avoiding-f
lto:buttl...@llnl.gov]
> Sent: 21 March 2011 20:46
> To: user@hbase.apache.org
> Subject: RE: HBase Stability
>
> Have you seen Todd Lipcon's post on MSLAB's?
> http://www.cloudera.com/blog/2011/02/avoiding-full-gcs-in-hbase-with-mem
> store-local-allocation-buffers-part-1/
table#setAutoFlush(false) ?
--- On Mon, 3/21/11, Buttler, David wrote:
> From: Buttler, David
> Subject: RE: HBase Stability
> To: "user@hbase.apache.org"
> Date: Monday, March 21, 2011, 1:46 PM
> Have you seen Todd Lipcon's post on
> MSLAB's?
24 matches
Mail list logo