I presume that in order to give you better answer you will need to answer some questions can you share your configuration? how many nodes hbase? are you sharing the data in mysql? Are hbase and hdfs on same nodes? What is the volume of the data you try to retrieve? Do you try a get during load? Did you enable bloom filters? what version of hbase are you using?
Regarding the multi-get, i'm not sure this is the best way to get 500-1000 records. did you try different size of batch? did you try to retrieve a single record? Mikael.S On Fri, Mar 2, 2012 at 9:37 PM, Oleg Ruchovets <[email protected]> wrote: > Hi. > > We are going to write to hbase 50-80 million records on daily basis. > Actually write performance is not critical. > We are going read relatively small amount of data 500-1000 records per > one request. > We use multiGet api (our assumption is fastest way to get 500-1000 > records is it correct?). > > Running a benchmark we get a results: > Read from hbase takes 2 seconds. > Reading the same records from MySql tooks 1 second. > > Difference is 100%. The questions is what is the way to speed up > hbase read operation. > > Thanks in advance. > Oleg. > -- Mikael.S
