[ https://issues.apache.org/jira/browse/HADOOP-19218?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17862579#comment-17862579 ]
Viraj Jasani commented on HADOOP-19218: --------------------------------------- Thread dump ref: {code:java} "IPC Server listener on 8020" #92 daemon prio=5 os_prio=0 tid=0x00007f23a9592800 nid=0x81744 runnable [0x00007f23ad38a000] java.lang.Thread.State: RUNNABLE at java.net.Inet4AddressImpl.lookupAllHostAddr(Native Method) at java.net.InetAddress$2.lookupAllHostAddr(InetAddress.java:867) at java.net.InetAddress.getAddressesFromNameService(InetAddress.java:1302) at java.net.InetAddress$NameServiceAddresses.get(InetAddress.java:815) - locked <0x00007f2bc29c6a10> (a java.net.InetAddress$NameServiceAddresses) at java.net.InetAddress.getAllByName0(InetAddress.java:1291) at java.net.InetAddress.getAllByName0(InetAddress.java:1211) at java.net.InetAddress.getHostFromNameService(InetAddress.java:637) at java.net.InetAddress.getHostName(InetAddress.java:562) at java.net.InetAddress.getHostName(InetAddress.java:534) at org.apache.hadoop.ipc.Server$Connection.<init>(Server.java:1916) at org.apache.hadoop.ipc.Server$ConnectionManager.register(Server.java:3841) at org.apache.hadoop.ipc.Server$Listener.doAccept(Server.java:1448) at org.apache.hadoop.ipc.Server$Listener.run(Server.java:1389) {code} > Avoid DNS lookup while creating IPC Connection object > ----------------------------------------------------- > > Key: HADOOP-19218 > URL: https://issues.apache.org/jira/browse/HADOOP-19218 > Project: Hadoop Common > Issue Type: Improvement > Reporter: Viraj Jasani > Assignee: Viraj Jasani > Priority: Major > > Been running HADOOP-18628 in production for quite sometime, everything works > fine as long as DNS servers in HA are available. Upgrading single NS server > at a time is also a common case, not problematic. Every DNS lookup takes 1ms > in general. > However, recently we encountered a case where 2 out of 4 NS servers went down > (temporarily but it's a rare case). With small duration DNS cache and 2s of > NS fallback timeout configured in resolv.conf, now any client performing DNS > lookup can encounter 4s+ delay. This caused namenode outage as listener > thread is single threaded and it was not able to keep up with large num of > unique clients (in direct proportion with num of DNS resolutions every few > seconds) initiating connection on listener port. > While having 2 out of 4 DNS servers offline is rare case and NS fallback > settings could also be improved, it is important to note that we don't need > to perform DNS resolution for every new connection if the intention is to > improve the insights into VersionMistmatch errors thrown by the server. > The proposal is the delay the DNS resolution until the server throws the > error for incompatible header or version mismatch. This would also help with > ~1ms extra time spent even for healthy DNS lookup. -- This message was sent by Atlassian Jira (v8.20.10#820010) --------------------------------------------------------------------- To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org