hbase hfile -p -f /hbase/data/default/ip_login/d0d7d881bb802592c09d305e47ae70a5/_d/7ec738167e9f4d4386316e5e702c8d3d

# 合并相邻的两个Region hbase> merge_region 'ENCODED_REGIONNAME', 'ENCODED_REGIONNAME' # 强制合并两个Region hbase> merge_region 'ENCODED_REGIONNAME', 'ENCODED_REGIONNAME', true

# Test Mode: # # hbase org.jruby.Main merge_empty_regions.rb namespace.tablename <skip_size> <batch_regions> <merge?> # # Non Test - ie actually do the merge: # # hbase org.jruby.Main merge_empty_regions.rb namespace.tablename <skip_size> <batch_regions> merge # # Note: Please replace namespace.tablename with your namespace and table, eg NS1.MyTable. This value is case sensitive.  require 'digest' require 'java' java_import org.apache.hadoop.hbase.HBaseConfiguration java_import org.apache.hadoop.hbase.client.HBaseAdmin java_import org.apache.hadoop.hbase.TableName java_import org.apache.hadoop.hbase.HRegionInfo; java_import org.apache.hadoop.hbase.client.Connection java_import org.apache.hadoop.hbase.client.ConnectionFactory java_import org.apache.hadoop.hbase.client.Table java_import org.apache.hadoop.hbase.util.Bytes def list_bigger_regions(admin, table, low_size) cluster_status = admin.getClusterStatus() master = cluster_status.getMaster() biggers = [] cluster_status.getServers.each do |s| cluster_status.getLoad(s).getRegionsLoad.each do |r| # getRegionsLoad returns an array of arrays, where each array # is 2 elements # Filter out any regions that don't match the requested # tablename next unless r[1].get_name_as_string =~ /#{table}\,/ if r[1].getStorefileSizeMB() > low_size if r[1].get_name_as_string =~ /\.([^\.]+)\.$/ biggers.push $1 else raise "Failed to get the encoded name for #{r[1].get_name_as_string}" end end end end biggers end # Handle command line parameters table_name = ARGV[0] low_size = 1024 if ARGV[1].to_i >= low_size low_size=ARGV[1].to_i end limit_batch = 1000 if ARGV[2].to_i <= limit_batch limit_batch = ARGV[2].to_i end do_merge = false if ARGV[3] == 'merge' do_merge = true end config = HBaseConfiguration.create(); connection = ConnectionFactory.createConnection(config); admin = HBaseAdmin.new(connection); bigger_regions = list_bigger_regions(admin, table_name, low_size) regions = admin.getTableRegions(Bytes.toBytes(table_name)); puts "Total Table Regions: #{regions.length}" puts "Total bigger regions: #{bigger_regions.length}" filtered_regions = regions.reject do |r| bigger_regions.include?(r.get_encoded_name) end puts "Total regions to consider for Merge: #{filtered_regions.length}" filtered_regions_limit = filtered_regions if filtered_regions.length < 2 puts "There are not enough regions to merge" filtered_regions_limit = filtered_regions end if filtered_regions.length > limit_batch filtered_regions_limit = filtered_regions[0,limit_batch] puts "But we will merge : #{filtered_regions_limit.length} regions because limit in parameter!" end r1, r2 = nil filtered_regions_limit.each do |r| if r1.nil? r1 = r next end if r2.nil? r2 = r end # Skip any region that is a split region if r1.is_split() r1 = r2 r2 = nil puts "Skip #{r1.get_encoded_name} bcause it in spliting!" next end if r2.is_split() r2 = nil puts "Skip #{r2.get_encoded_name} bcause it in spliting!" next end if HRegionInfo.are_adjacent(r1, r2) # only merge regions that are adjacent puts "#{r1.get_encoded_name} is adjacent to #{r2.get_encoded_name}" if do_merge admin.mergeRegions(r1.getEncodedNameAsBytes, r2.getEncodedNameAsBytes, false) puts "Successfully Merged #{r1.get_encoded_name} with #{r2.get_encoded_name}" sleep 2 end r1, r2 = nil else puts "Regions are not adjacent, so drop the first one and with the #{r2.get_encoded_name} to iterate again" r1 = r2 r2 = nil end end admin.close

#! /bin/bash  num=$1 echo "[`date "+%Y-%m-%d %H:%M:%S"`] INFO : RegionServer Start Merging..." if [ ! -n "$num" ]; then echo "[`date "+%Y-%m-%d %H:%M:%S"`] INFO : Default Merging 10 Times." num=10 elif [[ $num == *[!0-9]* ]]; then echo "[`date "+%Y-%m-%d %H:%M:%S"`] INFO : Input [$num] Times Must Be Number." exit 1 else echo "[`date "+%Y-%m-%d %H:%M:%S"`] INFO : User-Defined Merging [$num] Times." fi for (( i=1; i<=$num; i++ )) do echo "[`date "+%Y-%m-%d %H:%M:%S"`] INFO : Merging [$i] Times,Total [$num] Times." hbase org.jruby.Main merge_small_regions.rb namespace.tablename 10240 4000 merge sleep 5 done

# 默认循环10次，例如本次循环执行5次 sh merging-region.sh 5

for (RegionState state : regionsInTransition.values()) { HRegionInfo hri = state.getRegion(); if (assignedRegions.contains(hri)) { // Region is open on this region server, but in transition. // This region must be moving away from this server, or splitting/merging. // SSH will handle it, either skip assigning, or re-assign. LOG.info("Transitioning " + state + " will be handled by ServerCrashProcedure for " + sn); } else if (sn.equals(state.getServerName())) { // Region is in transition on this region server, and this // region is not open on this server. So the region must be // moving to this server from another one (i.e. opening or // pending open on this server, was open on another one. // Offline state is also kind of pending open if the region is in // transition. The region could be in failed_close state too if we have // tried several times to open it while this region server is not reachable) if (state.isPendingOpenOrOpening() || state.isFailedClose() || state.isOffline()) { LOG.info("Found region in " + state + " to be reassigned by ServerCrashProcedure for " + sn); rits.add(hri); } else if(state.isSplittingNew()) { regionsToCleanIfNoMetaEntry.add(state.getRegion()); } else { LOG.warn("THIS SHOULD NOT HAPPEN: unexpected " + state); } } }

for (RegionState state : regionsInTransition.values()) { HRegionInfo hri = state.getRegion(); if (assignedRegions.contains(hri)) { // Region is open on this region server, but in transition. // This region must be moving away from this server, or splitting/merging. // SSH will handle it, either skip assigning, or re-assign. LOG.info("Transitioning " + state + " will be handled by ServerCrashProcedure for " + sn); } else if (sn.equals(state.getServerName())) { // Region is in transition on this region server, and this // region is not open on this server. So the region must be // moving to this server from another one (i.e. opening or // pending open on this server, was open on another one. // Offline state is also kind of pending open if the region is in // transition. The region could be in failed_close state too if we have // tried several times to open it while this region server is not reachable) if (state.isPendingOpenOrOpening() || state.isFailedClose() || state.isOffline()) { LOG.info("Found region in " + state + " to be reassigned by ServerCrashProcedure for " + sn); rits.add(hri); } else if(state.isSplittingNew()) { regionsToCleanIfNoMetaEntry.add(state.getRegion()); } else if (isOneOfStates(state, State.SPLITTING_NEW, State.MERGING_NEW)) { regionsToCleanIfNoMetaEntry.add(state.getRegion()); }else { LOG.warn("THIS SHOULD NOT HAPPEN: unexpected " + state); } } }