Eli Collins wrote:
I presume it makes no sense to try to spread the NameNode across multiple
disks?
Not quite sure what you mean here, but dfs.name.dir (where the NN
stores its metadata) should have multiple directories on different
disks to guard against the failure of any single disk. Many
Thanks for your responses.
On Mon, Mar 1, 2010 at 2:48 AM, Terrence Martin
tmar...@physics.ucsd.edu wrote:
Mag Gam wrote:
I just setup my first hadoop cluster with 5 nodes. What is the best
way to check if replication is really working? I assume the best way
is to power down 2 nodes and
On Sun, Feb 28, 2010 at 5:27 PM, Eli Collins e...@cloudera.com wrote:
dfs.name.dir (where the NN
stores its metadata) should have multiple directories on different
disks to guard against the failure of any single disk. Many people
also use RAIDed disks and include an NFS mount in dfs.name.dir
On Mon, Mar 1, 2010 at 5:48 AM, Steve Loughran ste...@apache.org wrote:
Best of all: a secondary namenode to get the streamed event log, as that
will mean your cluster restarts faster. You do not want to lose your NN
data.
If the NN data is lost, all the HDFS data is functionally lost,
On 2/28/10 11:48 PM, Terrence Martin tmar...@physics.ucsd.edu wrote:
Mag Gam wrote:
I just setup my first hadoop cluster with 5 nodes. What is the best
way to check if replication is really working? I assume the best way
is to power down 2 nodes and see if I can still reach my data?
Well
On Mon, Mar 1, 2010 at 8:19 AM, Marc Farnum Rendino mvg...@gmail.com wrote:
On Sun, Feb 28, 2010 at 5:27 PM, Eli Collins e...@cloudera.com wrote:
dfs.name.dir (where the NN
stores its metadata) should have multiple directories on different
disks to guard against the failure of any single
We also created a Meetup group in case you prefer to register on meetup.com
http://www.meetup.com/Hive-User-Group-Meeting/calendar/12741356/
We are hosting a Hive User Group Meeting, open to all current and
potential hadoop/hive users.
Agenda:
* Hive Tutorial (Carl Steinbach, cloudera): 20 min
Avro 1.3.0 is now available.
In this release:
- the Avro file format has been revised and simplified;
- the source tree and release artifacts have been restructured;
- the Java port has been significantly optimized;
- the Python port has been largely rewritten;
- the C port is now
Hadoop 0.20.2 is released and propagating to mirrors. The list of
changes may be found in the release notes:
http://bit.ly/dd6rwL
And in JIRA:
COMMON: http://bit.ly/9fDo2f
MAPREDUCE: http://bit.ly/aD0BM5
HDFS: http://bit.ly/ckvMfO
Thanks to everyone who worked on this release. -C
On Mon, Mar 1, 2010 at 2:00 PM, Eli Collins e...@cloudera.com wrote:
Yes, it's good to have multiple directories as well as may each or at
least some of the directories reliable, eg below
/data/N/dfs/namenode are local disks and /mnt/filer-hdfs is a
reliable NFS filer.
namedfs.name.dir/name
Marc,
You might find my preso I did on Hadoop at Apachecon EU last year handy:
http://wiki.apache.org/hadoop/HadoopPresentations?action=AttachFiledo=view;
target=aw-apachecon-eu-2009.pdf
aka
http://bit.ly/d3UU4A
It talks a bit about the care and feeding of your Hadoop grid, including how
to
On Mon, Mar 1, 2010 at 7:20 PM, Allen Wittenauer
awittena...@linkedin.comwrote:
You might find my preso I did on Hadoop at Apachecon EU last year handy...
Terrific; thanks!
- Marc
There's work on trunk to add a backup name node which gets a
stream of edits from the NN so it has an update copy of the metadata.
Ah; I think this is alluded to in the conf file, right?
It's dfs.namenode.backup.* in conf files but you probably haven't
bumped into them unless you're using
13 matches
Mail list logo
