HBase, mail # user - Re: Hbase tuning for heavy write cluster - 2014-01-27, 18:38
Solr & Elasticsearch trainings in New York & San Francisco [more info][hide]
 Search Hadoop and all its subprojects:

Switch to Threaded View
Copy link to this message
-
Re: Hbase tuning for heavy write cluster
On Sun, Jan 26, 2014 at 4:13 PM, Rohit Dev <[EMAIL PROTECTED]> wrote:
Hotspotting on regions hosted on this server?  If more than one hot region,
move the hot regions around the cluster?

Pastebin tail of this particular RS if that is ok to do?
Any complaints in dmessage?  (Disks?)
Took a quick look and handlers are hanging out waiting on response from
HDFS.

Short-circuit reads enabled?
Beating all disks equally or focused on single disk?
Compactions are not completing?  This server is hosting the 'big' region
with many store files?
(The above needs doc'ing in the refguide)

The above message comes when you are writing at a rate that the server is
having trouble keeping up with.  The RS is carrying more than the
configured amount of WALs and so we are complaining and acting to clean up
excess.  It is not a 'problem' if we are not too far beyond your configured
maximum (90 in this case which is a lot -- many WALs means there is more to
replay when a server crashes so getting regions back on line takes longer).

St.Ack

 
NEW: Monitor These Apps!
elasticsearch, apache solr, apache hbase, hadoop, redis, casssandra, amazon cloudwatch, mysql, memcached, apache kafka, apache zookeeper, apache storm, ubuntu, centOS, red hat, debian, puppet labs, java, senseiDB