hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Yves Langisch <y...@langisch.ch>
Subject Re: Scan Metrics in Ganglia
Date Mon, 23 Jan 2012 22:11:36 GMT
Can you please more elaborate on this metric? I've ganglia for collecting the metrics (poll
interval is 15s) and I see a constant value for hbase.regionserver.requests which is around
6700 requests. What does that mean exactly? 6700 unprocessed requests at this point in time?

-
Yves
 
On Dec 1, 2011, at 9:15 PM, Doug Meil wrote:

> 
> This can be a bit tricky because of the scan caching, for example...
> 
> http://hbase.apache.org/book.html#rs_metrics
> 
> 12.4.2.14. hbase.regionserver.requests
> 
> Total number of read and write requests.  Requests correspond to
> RegionServer
> RPC calls, thus a single Get will result in 1 request, but a Scan with
> caching set to 1000 will result in 1 request for each 'next' call (i.e.,
> not each row).  A bulk-load request will constitute 1 request per
> HFile.
> 
> 
> 
> 
> 
> 
> On 12/1/11 2:23 PM, "sagar naik" <snaik@attributor.com> wrote:
> 
>> Hi,
>> I can see metrics for get calls (number of get , avg time for get)
>> However, I could not do so for scan calls
>> 
>> Please let me know how can I measure
>> 
>> Thanks
>> -Sagar
>> 
> 
> 


Mime
View raw message