Apache HBase is a rapidly-evolving random-access distributed data store built on top of Apache Hadoop's HDFS and Apache ZooKeeper. Drawing from real-world support experiences, this talk provides administrators insight into improving HBase's availability and recovering from situations where HBase is not available. We share tips on the common root causes of unavailability, explain how to diagnose them, and prescribe measures for ensuring maximum availability of an HBase cluster. We discuss new features that improve recovery time such as distributed log splitting as well as supportability improvements. We will also describe utilities including new failure recovery tools that we have developed and contributed that can be used to diagnose and repair rare corruption problems on live HBase systems.
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
Hadoop Summit 2012 | Improving HBase Availability and Repair
1. Improving HBase Availability and Repair
Improving HBase Availability and Repair
Jeff Bean, Jonathan Hsieh
{jwfbean,jon}@cloudera.com
6/13/12
2. Who Are We?
• Jeff Bean
• Designated Support Engineer, Cloudera
• Education Program Lead, Cloudera
• Jonathan Hsieh
• Software Engineer, Cloudera
• Apache HBase Committer and PMC member
Hadoop Summit 2012. 6/13/12 Copyright 2012 2
Cloudera Inc, All Rights Reserved
3. What is Apache HBase?
Apache HBase is an
reliable, column-
oriented data store
that provides
consistent, low-
latency, random
read/write access.
Hadoop Summit 2012. 6/13/12 Copyright 2012 3
Cloudera Inc, All Rights Reserved
4. Fault Tolerance vs Highly Available
• Fault tolerant:
• Ability to recover service if a
component fails, without losing
Fault Tolerant
data.
• Highly Available:
• Ability to quickly recover service if Highly
a component fails, without losing Available
data.
• Goal: Minimize downtime!
Hadoop Summit 2012. 6/13/12 Copyright 2012 4
Cloudera Inc, All Rights Reserved
5. HBase Architecture
• HBase is designed to be fault tolerant
and highly available
• It depends on other systems to be as well.
App MR
• Replication for fault tolerance
• Serve regions from any Region server
• Failover HMasters
• ZK Quorums
• HDFS Block replication on Data Nodes
ZK HDFS
• But replication doesn’t guarantee high
availability
• There can still be software or human faults
Hadoop Summit 2012. 6/13/12 Copyright 2012 5
Cloudera Inc, All Rights Reserved
6. Causes of HBase Downtime
HBase Downtime
Distribution
• Unplanned Maintenance
• Hardware failures
• Software errors
Planned
• Human error
• Planned Maintenance
• Upgrades Unplanned
• Migrations
Hadoop Summit 2012. 6/13/12 Copyright 2012 6
Cloudera Inc, All Rights Reserved
7. Causes of Unexpected Maintenance Incidents
Unplanned Maintenance: Root
Cause from Cloudera Support
• Misconfiguration
• Metadata Corruptions
Repair
• Network / HW problems Needed
HBase, ZK,
28%
• SW problems MR, HDFS
Misconfig
44%
Fix
• Long recovery time HW/NW
16% Patch
• Automated and manual Required
12%
Source: Cloudera’s production HBase Support Tickets
CDH3’s HBase 0.90.x, Hadoop 0.20.x/1.0.x
Hadoop Summit 2012. 6/13/12 Copyright 2012 7
Cloudera Inc, All Rights Reserved
8. Outline
• Where we were
• HBase 0.90.x + Hadoop 0.20.x/1.0.x
• Case Studies
• Where we are today
• HBase 0.92.x/0.94.x + Hadoop 2.0.x
• Feature Summary
• Where we are going
• HBase 0.96.x + Hadoop 2.x
• Feature Preview
Hadoop Summit 2012. 6/13/12 Copyright 2012 8
Cloudera Inc, All Rights Reserved
9. [T]here are known knowns; there are things we know we know.
We also know there are known unknowns; that is to say we know
there are some things we do not know.
But there are also unknown unknowns – there are things we do not
know we don't know.
—United States Secretary of Defense Donald Rumsfeld
WHERE WE WERE:
CASE STUDIES
Hadoop Summit 2012. 6/13/12 Copyright 2012 9
Cloudera Inc, All Rights Reserved
10. Best Practices to avoid hazards
Unplanned Maintenance: Root
Cause from Cloudera Support
Repair
Needed
HBase, ZK,
28%
MR, HDFS
Misconfig
44%
Fix
HW/NW
16% Patch
Required
12%
CAN PREVENT HBASE Source: Cloudera’s production HBase Support Tickets
MISCONFIGURATIONS CDH3’s HBase 0.90.x, Hadoop 0.20.x/1.0.x
Hadoop Summit 2012. 6/13/12 Copyright 2012 10
Cloudera Inc, All Rights Reserved
11. Case #1: Memory Over-subscription Hazard
Misconfig Bad Outcome
Masters Take
Node A swaps
• Too many MR Slots • MapReduce tasks fail Action
• MR Slots too large • HDFS datanode
• “Arbitrary” processes operations time out • JobTracker blacklists TT
pause or unresponsive on node B
• HBase client operations
fail • Jobs fail or run slow
• NameNode re-replicates
blocks from node A
Node A Under Node B can’t
Load connect to node A
Hadoop Summit 2012. 6/13/12 Copyright 2012 11
Cloudera Inc, All Rights Reserved
12. Case #2, #3: Hazards of Abusing HDFS and ZK
Millions of HDFS files Millions of ZK nodes
Bad Practice Misconfiguration
500,000 blocks per Millions of ZK znodes
datanode 400MB snapshot
Heartbeat thread SW Bug ZK fails to create new
blocks IO snapshots, fails
RS cannot access Bad outcome
HBase goes down
HDFS
HBase goes down Bad outcome HBase fails to restart
SW Bug, Worse
Hadoop Summit 2012. 6/13/12 Copyright 2012
outcome 12
Cloudera Inc, All Rights Reserved
13. Case #4: Splitting Corruption from HW failure
Manual, Slow, and
HW Failure requires expert
HBase has
Region regions Multiple 6 hour
Network failure Split Recovery
attempts to inconsistencies manual repair
(takes out NN) incomplete
split (overlaps / sessions.
holes)
SW Bug
Hadoop Summit 2012. 6/13/12 Copyright 2012 13
Cloudera Inc, All Rights Reserved
14. Case #5: Slow recovery from HW failure
Correct but slow!
Human error
On
RS loses restart, Roo 9 hour hlog
Network Manual
HDFS, WAL t and splitting
HW failure Repairs
s .META. recovery
assign fails
SW error
Hadoop Summit 2012. 6/13/12 Copyright 2012 14
Cloudera Inc, All Rights Reserved
15. Initial Lessons
• Use Best practices to avoid problems
• Conservative first
• Avoid unstable features
• What can we do?
• Fix the bugs
• Recover from problems faster
• Make people smarter to avoid hazards and misconfigurations
• Make software smarter to prevent hazards and
misconfigurations
Hadoop Summit 2012. 6/13/12 Copyright 2012 15
Cloudera Inc, All Rights Reserved
16. In war, then, let your great object be
victory, not lengthy campaigns.
-- Sun Tzu
WHERE WE ARE TODAY
HBASE 0.92.X + HADOOP 2.0.X
Hadoop Summit 2012. 6/13/12 Copyright 2012 16
Cloudera Inc, All Rights Reserved
17. Goal: Reduce unexpected downtime by
recovering faster
• Removing the SPOFs
• HA HDFS
• Faster Recovery
• Improved hbck
• Distributed Log splitting
Hadoop Summit 2012. 6/13/12 Copyright 2012 17
Cloudera Inc, All Rights Reserved
18. Problem: HDFS NN goes down under HBase
• HBase depends on HDFS. MR
App
• If HDFS is down, HBase goes down.
• Ramifications.
• Forces Recovery mechanism
• Caused some data corruptions
ZK HDFS
• Ideally we avoid having to do recovery at all.
Hadoop Summit 2012. 6/13/12 Copyright 2012 18
Cloudera Inc, All Rights Reserved
19. HBase-HDFS HA Nodes
NameNode (active) HMaster
(metadata server) (region metadata)
NameNode (standby) HMaster
(active-standby (hot standby)
hot failover)
ZooKeeper Quorum
HDFS DataNodes HBase RegionServers
Hadoop Summit 2012. 6/13/12 Copyright 2012 19
Cloudera Inc, All Rights Reserved
20. HBase-HDFS HA Nodes: Transparent to HBase
HMaster
(region metadata)
HMaster
NameNode (active) (hot standby)
ZooKeeper Quorum
HDFS DataNodes HBase RegionServers
Hadoop Summit 2012. 6/13/12 Copyright 2012 20
Cloudera Inc, All Rights Reserved
21. HBase-HDFS HA Nodes: No more SPOF
HMaster
NameNode (active) (active)
ZooKeeper Quorum
HDFS DataNodes HBase RegionServers
Hadoop Summit 2012. 6/13/12 Copyright 2012 21
Cloudera Inc, All Rights Reserved
22. Recovery operations
• If a network switch fails or if there is a power outage,
• HBase, ZK, and HA HDFS will fail
• Will always still rely on recovery mechanisms.
• Need to be able to quickly recover
• Metadata Invariants to fix metadata corruptions
• Data Consistency to restore ACID guarantees
Hadoop Summit 2012. 6/13/12 Copyright 2012 22
Cloudera Inc, All Rights Reserved
23. HBase Metadata Corruptions
• Internal HBase metadata Unplanned Maintenance: Root Cause
corruptions from Cloudera Support
• Prevent HBase from starting
• Cause some regions to be Repair
unavailable. Needed
28% HBase, ZK,
MR, HDFS
Misconfig
• Repairs are intricate and 44%
Fix
can cause extended periods HW/NW
of downtime. 16% Patch
Required
12%
Hadoop Summit 2012. 6/13/12 Copyright 2012 23
Cloudera Inc, All Rights Reserved
24. HBase Metadata Invariants
Table Integrity Region Consistency
• Every key shall get assigned • Metadata about regions should
to a single region. agree in hdfs, meta and region
server assignment.
[‘ ‘,A)
[A,B) regioninfo
in META
[B, C)
[C, D)
[D, E) Good
[E, F) region
assigned .regioninfo
[F, G) to RS in HDFS
[G, ‘ ‘)
Hadoop Summit 2012. 6/13/12 Copyright 2012 24
Cloudera Inc, All Rights Reserved
25. Detecting and Repairing corruption with hbck
• HBase 0.90 hbck
• Checks an HBase
instance’s internals
invariants.
• HBase hbck today
• Checks and can fix
problem in an HBase
instance’s internal
invariants
• 0.90.7, 0.92.2, 0.9
4.0
• CDH3u4, CDH4
Hadoop Summit 2012. 6/13/12 Copyright 2012 25
Cloudera Inc, All Rights Reserved
26. Case #4 redux: Splitting Corruption
Manual, Slow, and
HW Failure requires expert
HBase has
Region Network failure regions Multiple 6 hour
Split Recovery
attempts to inconsistencies manual repair
(takes out NN) incomplete
split (overlaps / sessions.
holes)
SW Bug
Hadoop Summit 2012. 6/13/12 Copyright 2012 26
Cloudera Inc, All Rights Reserved
27. Case #4 redux: Splitting Corruption
HW Failure
HBase has
Region Network failure regions Automated
Split Recovery
attempts to inconsistencies repair tool
(takes out NN) incomplete
split (overlaps / (Minutes)
holes)
Fixes are
SW Bug
quicker, operator
can use
Hadoop Summit 2012. 6/13/12 Copyright 2012 27
Cloudera Inc, All Rights Reserved
28. Case #4 redux: Splitting Corruption
HW Failure
Minor HBase
Region Network failure inconsistencies Automated
Split Recovery
attempts to repair tool
(takes out NN) incomplete (bad
split (seconds)
assignments)
Fixed SW Bug
Hadoop Summit 2012. 6/13/12 Copyright 2012 28
Cloudera Inc, All Rights Reserved
29. Data Consistency
• When a region server goes down, it tries to flush data in
memory to HDFS.
• If it cannot write to HDFS, it relies on the WAL/HLog.
• Recovery via the HLog is vital to prevent data loss
• Understand the write path.
• Recovery: HLog splitting.
• Faster Recovery: Distributed HLog splitting.
Hadoop Summit 2012. 6/13/12 Copyright 2012 29
Cloudera Inc, All Rights Reserved
30. Write Path (Put / Delete / Increment)
HBase
Region Server
client
HLog Put
Server
HRegion HRegion
MemStore MemStore
Put
HStore
HStore
HStore
HStore
Hadoop Summit 2012. 6/13/12 Copyright 2012 30
Cloudera Inc, All Rights Reserved
31. Write Path (Put / Delete / Increment)
Note, both regions
write to the same
HBase HLog
Region Server
client
Put
HLog Put Put
Server
HRegion HRegion
MemStore MemStore
Put Put
HStore
HStore
HStore
HStore
Hadoop Summit 2012. 6/13/12 Copyright 2012 31
Cloudera Inc, All Rights Reserved
32. Log Splitting
HMaster
RegionServer RegionServer RegionServer
HLog1 HLog2 HLog3
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
mem mem mem mem mem mem
Hadoop Summit 2012. 6/13/12 Copyright 2012 32
Cloudera Inc, All Rights Reserved
33. Log Splitting
HMaster
RegionServer RegionServer RegionServer
HLog1 HLog2 HLog3
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
mem mem mem mem mem mem
Hadoop Summit 2012. 6/13/12 Copyright 2012 33
Cloudera Inc, All Rights Reserved
39. Log Splitting Whew. I did a lot of
splitting work. That
HMaster took 9 hours!
HLog HLog HLog
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
Hadoop Summit 2012. 6/13/12 Copyright 2012 39
Cloudera Inc, All Rights Reserved
40. Log Splitting RegionServers, here
are your region
HMaster assignments.
RegionServer4 RegionServer5 RegionServer6
…
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
Hadoop Summit 2012. 6/13/12 Copyright 2012 40
Cloudera Inc, All Rights Reserved
41. Log Splitting Victory!
HMaster
RegionServer4 RegionServer5 RegionServer6
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
mem mem mem mem mem mem
Hadoop Summit 2012. 6/13/12 Copyright 2012 41
Cloudera Inc, All Rights Reserved
42. Can we recover more quickly?
• In the case study, this is all done serially by the master
• The master took 9 hours to recovery.
• The 100 region server nodes were idle.
• Let’s use the idle machines to do splitting in parallel!
• Distributed log splitting (HBASE-1364)
• Introduced in 0.92.0 by Prakash Khemani (Facebook)
• Included in CDH4 (0.92.1)
• Backported to CDH3u3 (off by default)
Hadoop Summit 2012. 6/13/12 Copyright 2012 42
Cloudera Inc, All Rights Reserved
43. Distributed Log Splitting I’m the boss.
HMaster
RegionServer RegionServer RegionServer
HLog1 HLog2 HLog3
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
mem mem mem mem mem mem
Hadoop Summit 2012. 6/13/12 Copyright 2012 43
Cloudera Inc, All Rights Reserved
44. Distributed Log Splitting There is a lot of
splitting work here,
HMaster let’s split it up.
HLog1 HLog2 HLog3
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
Hadoop Summit 2012. 6/13/12 Copyright 2012 44
Cloudera Inc, All Rights Reserved
45. Distributed Log Splitting You guys do the work
for me.
HMaster
RegionServer4 RegionServer5 RegionServer6
HLog1 HLog2 HLog3
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
Hadoop Summit 2012. 6/13/12 Copyright 2012 45
Cloudera Inc, All Rights Reserved
46. Distributed Log Splitting You guys do the work
for me.
HMaster
RegionServer4 RegionServer5 RegionServer6
HLog1 HLog2 HLog3
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
Hadoop Summit 2012. 6/13/12 Copyright 2012 46
Cloudera Inc, All Rights Reserved
47. Distributed Log Splitting Great, that took 5.4
minutes.
HMaster
RegionServer4 RegionServer5 RegionServer6
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
Hadoop Summit 2012. 6/13/12 Copyright 2012 47
Cloudera Inc, All Rights Reserved
48. Distributed Log Splitting Good Job, here are
your region
HMaster assignments.
RegionServer4 RegionServer5 RegionServer6
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
Hadoop Summit 2012. 6/13/12 Copyright 2012 48
Cloudera Inc, All Rights Reserved
49. Distributed Log Splitting Like a Boss.
HMaster
RegionServer4 RegionServer5 RegionServer6
…
HRegion
HRegion
HRegion
HRegion
HRegion
HRegion
mem mem mem mem mem mem
Hadoop Summit 2012. 6/13/12 Copyright 2012 49
Cloudera Inc, All Rights Reserved
50. Case #5 redux: Network failure and slow recovery
Correct but slow!
Human error
On
RS loses restart, Roo 9 hour hlog
Network Manual
HDFS, WAL t and splitting
HW failure Repair
s .META. recovery
assign fails
Hadoop Summit 2012. 6/13/12 Copyright 2012 50
Cloudera Inc, All Rights Reserved
51. Case #5 redux: Network failure and slow recovery
Correct and Faster!
Human error
On
5.4 Minute
RS loses restart, Roo
Network Automatic hlog
HDFS, WAL t and
HW failure repairs splitting
s .META.
recovery
assign fails
Fixed!
Hadoop Summit 2012. 6/13/12 Copyright 2012 51
Cloudera Inc, All Rights Reserved
52. WHERE WE ARE GOING
HBASE 0.96 + HADOOP 2.X
Hadoop Summit 2012. 6/13/12 Copyright 2012 52
Cloudera Inc, All Rights Reserved
53. Themes
• Minimizing Planned downtime HBase Downtime
• Changing configurations Distribution
• Online Schema Change
(experimental in 0.92, 0.94)
• Rolling Restarts Planned
• Wire compatibility
Unplanned
Hadoop Summit 2012. 6/13/12 Copyright 2012 53
Cloudera Inc, All Rights Reserved
54. Table unavailable when changing schema
• Changing table schema requires disabling table
• disable table, alter table schema, enable table
• Schema includes compression, cf’s, caching, ttl, versions.
• Goal: Quickly change table and column configuration
settings without having to disable Hbase tables.
• Feature Online Schema Change (HBASE-1730)
• Included in but considered experimental in HBase 0.92/0.94.
• Contributed by Facebook
Hadoop Summit 2012. 6/13/12 Copyright 2012 54
Cloudera Inc, All Rights Reserved
55. Changing Server Configs and Software updates
• Rolling restart is an operation for upgrading an HBase
cluster to a compatible version while keeping HBase
available and serving data.
• Handle server config changes.
• Handle code changes like hotfixes or compatible upgrades
Hadoop Summit 2012. 6/13/12 Copyright 2012 55
Cloudera Inc, All Rights Reserved
56. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 56
Cloudera Inc, All Rights Reserved
57. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 57
Cloudera Inc, All Rights Reserved
58. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 58
Cloudera Inc, All Rights Reserved
59. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 59
Cloudera Inc, All Rights Reserved
60. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 60
Cloudera Inc, All Rights Reserved
61. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 61
Cloudera Inc, All Rights Reserved
62. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 62
Cloudera Inc, All Rights Reserved
63. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 63
Cloudera Inc, All Rights Reserved
64. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 64
Cloudera Inc, All Rights Reserved
65. Rolling Restart
Admin
operations
ZK
Client Shell
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 65
Cloudera Inc, All Rights Reserved
66. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 66
Cloudera Inc, All Rights Reserved
67. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 67
Cloudera Inc, All Rights Reserved
68. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 68
Cloudera Inc, All Rights Reserved
69. Rolling Restart
Admin
operations
ZK
Client Shell
HM1
User
operations
HM2
RS1 RS2 RS3 RS4
Internal
operations
Hadoop Summit 2012. 6/13/12 Copyright 2012 69
Cloudera Inc, All Rights Reserved
70. Rolling restart limitations
• There are limitations on Unplanned Maintenance: Root
rolling restarts Cause from Cloudera Support
• All Servers and clients must be
wire compatible
• All must be able to read old
data in FS and ZK. Repair
Needed
HBase, ZK,
28%
• Ramifications: MR, HDFS
Misconfig
• Only minor version upgrades 44%
possible Fix
• New features that change RPCs HW/NW
require custom compatibility 16% Patch
shims. Required
• Data format changes not 12%
possible across minor versions.
Source: Cloudera’s production HBase Support Tickets
CDH3’s HBase 0.90.x, Hadoop 0.20.x/1.0.x
Hadoop Summit 2012. 6/13/12 Copyright 2012 70
Cloudera Inc, All Rights Reserved
71. HBase Compatibility and Extensibility
• Coming in HBase 0.96
• HBASE-5305 and friends
• Goals:
• Allow API and changes and persistent data structure changes
while guarantees compatibility between different minor
versions (0.96.0 -> 0.96.1)
• HBase client server compatibility between Major Versions.
(0.96.x -> 0.98.x)
Hadoop Summit 2012. 6/13/12 Copyright 2012 71
Cloudera Inc, All Rights Reserved
72. HDFS Wire Compatibility
• Here in HDFS 2.0.x
• HADOOP-7347 and friends
App MR
• Goals:
• Allow API and changes while
guaranteeing wire compatibility
between different minor versions
• HDFS client server compatibility ZK HDFS
between Major Versions.
Hadoop Summit 2012. 6/13/12 Copyright 2012 72
Cloudera Inc, All Rights Reserved
73. HDFS Wire Compatibility
• Here in HDFS 2.0.x
• HADOOP-7347 and friends
App MR
• Goals:
• Allow API and changes while
guaranteeing wire compatibility
between different minor versions
• HDFS client server compatibility ZK HDFS
between Major Versions.
Hadoop Summit 2012. 6/13/12 Copyright 2012 73
Cloudera Inc, All Rights Reserved
74. CONCLUSIONS
Hadoop Summit 2012. 6/13/12 Copyright 2012 74
Cloudera Inc, All Rights Reserved
75. Improving how we handling causes of downtime
Unplanned Maintenance: Root
HBase Downtime Distribution
Cause from Cloudera Support
Wire
compat Best
hbck practices
Repair
Planned
Needed
HBase, ZK,
28%
MR, HDFS
Misconfig
44%
Unplanned
Fix
HW/NW
16% Patch
Required
hbck and 12%
distributed log Wire
splitting compat
Hadoop Summit 2012. 6/13/12 Copyright 2012 75
Cloudera Inc, All Rights Reserved
76. jon@cloudera.com
Twitter: @jmhsieh
We’re hiring!
QUESTIONS?
Hadoop Summit 2012. 6/13/12 Copyright 2012 76
Cloudera Inc, All Rights Reserved
Notas del editor
This pie chart is a product from analyzing critical production Hbase tickets over the past 6 months: misconfig 44%, patch 12%,hw/nw 16%, repair 28%. Meaning that correcting a misconfig was all that it took to bring Hbase back up again. As you can see, misconfigurations and bugs break the most HBase clusters. Fixing bugs is up to the community. Fixing misconfigurations is up to you and the focus of the next segment. Because it’s hard to diagnose, misconfigurations are not what you want to spend your time on.If your cluster is broken, it’s probably a misconfiguration. This is a hard problem becausethe error messages are not tightly tied to the root cause.
CDH3 goes GA 4/12/12
HDFS-2379
CDH4 GA 6/5/12
Tested under HBase
Transparent to clients
Coupled with HBase Master failover means no SPOF
Cause:Disconnect a region server for a whileKill -9 a region serverWhy?All writes at a region server go to a single Hlog. This can contain edits from multiple regions. Regions my get reassigned to multiple other region servers.Need to split up the hlog
Region_mover.rbMove regions off, recording which regions were presentRestore regions, based on recorded regions Still mostly a manual process
Region_mover.rbMove regions off, recording which regions were presentRestore regions, based on recorded regions Still mostly a manual process