shrijeet

package com.example;

import java.io.*;
import java.util.List;
import java.util.regex.Pattern;

import com.google.protobuf.Descriptors.FieldDescriptor;
import com.google.protobuf.Descriptors.FieldDescriptor.JavaType;
import com.example.generated.LogFileProtos.LogFile;

shrijeet

{
  "processingtimems": 25255,
  "client": "172.22.4.5:56750",
  "timeRange     ": [
    0,
    9223372036854775807
  ],
  "starttimems": 1335310563560,
  "responsesize": 0,
  "class": "HRegionServer",

shrijeet

2012-04-24 20:00:02
Full thread dump Java HotSpot(TM) 64-Bit Server VM (14.2-b01 mixed mode):

"Attach Listener" daemon prio=10 tid=0x00002aaaf680f800 nid=0x2f2e waiting on condition [0x0000000000000000]
   java.lang.Thread.State: RUNNABLE

"IPC Client (47) connection to inw-5.rfiserve.net/172.22.4.5:60000 from hbase" daemon prio=10 tid=0x00002aaaf847e000 nid=0x2ee3 in Object.wait() [0x000000005960b000]
   java.lang.Thread.State: TIMED_WAITING (on object monitor)
	at java.lang.Object.wait(Native Method)
	- waiting on <0x00002aaaae8e5018> (a org.apache.hadoop.hbase.ipc.HBaseClient$Connection)

shrijeet

St^Ack: Sorry I was away. It is just spinning
shrijeet: I had wr itten a nice sequence of events , but then pastie.org decided to go down
shrijeet: anyways, here is the sequence 1) Launch a scanner which is slow, example scan hits once in billion 2) see entry in rs active calls list of type 'next'
shrijeet: 3) as soon that next call hits 60 second mark one more entry in rpc call list appears, this new rpc call is 'close'
shrijeet: 4) client does not see the exception untill close hits 60 second mark
shrijeet: 5) client dies once it sees exception (after 2 minutes) but next and close continue remotely
shrijeet: 6) they hang out in active call list of >30 minutes then they go away, region server spits our some warning in between
shrijeet: The warnings being org.apache.hadoop.hbase.UnknownScannerException, org.apache.hadoop.ipc.HBaseServer (output error) etc.
shrijeet: Here is a JSON snapshot of the state I described in (6) http://pastie.org/3842252

shrijeet

12/04/24 21:08:07 INFO client.ScannerCallable: sending close on rs for : {"timeRange":[0,9223372036854775807],"batch":-1,"startRow":"userprofile,,00000000000000","stopRow":"","totalColumns":1,"cacheBlocks":true,"families":{"info":["ALL"]},"maxVersions":1,"caching":-1}
Openning to file /user/shrijeet/afile to write results
Starting scanning table userprofile ...
12/04/24 21:09:12 INFO client.ScannerCallable: sending close on rs for : {"timeRange":[0,9223372036854775807],"batch":-1,"startRow":"userprofile,,00000000000000","stopRow":"","totalColumns":1,"cacheBlocks":true,"families":{"info":["ALL"]},"maxVersions":1,"caching":-1}
12/04/24 21:09:12 INFO client.HTable$ClientScanner: calling close on scanner for callable : {"timeRange":[0,9223372036854775807],"batch":-1,"startRow":"","stopRow":"","totalColumns":0,"cacheBlocks":true,"families":{},"maxVersions":1,"caching":50}
12/04/24 21:09:12 INFO client.ScannerCallable: sending close on rs for : {"timeRange":[0,9223372036854775807],"batch":-1,"startRow":"","stopRow"

shrijeet

public class ThriftSerialization extends com.esotericsoftware.kryo.Serializer {

    Map<Class, TBase> prototypes;
    TSerializer ser;
    TDeserializer des;
    
    public ThriftSerialization() {
        prototypes = new HashMap<Class, TBase>();
        ser = new TSerializer(new TCompactProtocol.Factory());
        des = new TDeserializer(new TCompactProtocol.Factory());               

shrijeet

public abstract class PBSerialize<T extends Message> extends
        Serializer {

    protected abstract T parseForm(CodedInputStream in);

    private final ThreadLocal<byte[]> thread_local_buffer = new ThreadLocal<byte[]>() {
        @Override
        protected byte[] initialValue() {
            return new byte[1024 * 10]; // 10 KB
        }

shrijeet

#!/usr/bin/env python
import sys
import os

"""
Modify this config section based on needs
1) hostrack_data : a file containing lines, a line represents one host
2) field_sep: separator used for fields in one line
3) log: disable/enable logging 

shrijeet

From 2fd88425c5848059fbefc7f85ce14858bbbe7775 Mon Sep 17 00:00:00 2001
From: Shrijeet Paliwal <[email protected]>
Date: Mon, 18 Jun 2012 14:25:21 -0700
Subject: [PATCH] Support client RPC operation level timeout

---
 Makefile                     |    1 +
 src/GetRequest.java          |   24 ++++++++++++++++++++++--
 src/HBaseClient.java         |   16 ++++++++++++++++
 src/HBaseRpc.java            |   24 ++++++++++++++++++++++++

shrijeet

<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<!-- Put site-specific property overrides in this file. -->

<configuration>

<property>
  <name>mapred.job.tracker</name>
  <value>MASTER:8021</value>