On Fri, Mar 23, 2012 at 12:40 AM, Juhani Connolly <[email protected]> wrote: > Status update: > > - We moved to cdh 4b1, so hbase 0.92 and hdfs 0.23(until now we were > using 0.20.2 series)
There is little experience running hbase on hadoop 0.23. > BUT, our write throughput has gone in the dump. If we disable wal > writes, we still get nearly 40,000 a second, but with it on, we're > lucky to get more than 12,000. Before we were getting as high as > 70,000 grouping puts together. Have set up log collection, and am not > finding anything unusual in the logs. > You are batching your writes? Can you paste your configs up on pastebin? And its not a case of high iowait? All else is working properly? No hardware misconfigs or bad switches/nics? (See the yfrog fellows slide deck where they tell a story about all the interesting things they found in their setup apart from hbase configs:http://www.slideshare.net/jacque74/hug-hbase-presentation). St.Ack
