Thanks St, I found that when running closing parent region to prepare for split, preflush occurred. But for some reason, an IOException throwed from hdfsclient, and caused preflush failed. Then split failed. We have made some change on HDFS and will check why Exception happened. But I don't know details on how hbase handle the exception. When rolling back the split operation, will it reset writestate.writesEnabled to true? If not, it will hanging writestate.writesEnabled to false and causing all other flush operations false.
Zhou Shuaifeng(Frank) -----邮件原件----- 发件人: [email protected] [mailto:[email protected]] 代表 Stack 发送时间: 2011年4月26日 0:10 收件人: [email protected] 抄送: Yanlijun 主题: Re: "NOT flushing memstore for region" keep on printing for half an hour Please fix this: ulimit -n 1024 Read the requirements section: http://hbase.apache.org/book/notsoquick.html#requirements. In particular see the ulimit/nproc section. Regards the below, we are in this bit of code: http://hbase.apache.org/xref/org/apache/hadoop/hbase/regionserver/HRegion.html#869 It looks like that region is closing at the time as you say. Maybe there is something in here. Please file an issue and include more of the log and we'll dig in. Thanks for writing the list. St.Ack
