This document provides a summary of a presentation on GC tuning confessions of a performance engineer. It begins with introductions of the speaker and an overview of topics to be covered, including performance engineering, insight into garbage collectors, OpenJDK HotSpot GCs, GC algorithms, key topics, and GC tunables. The document then goes into more detail on various GC algorithms like Parallel GC, CMS GC, and G1 GC. It discusses concepts like promotion failures, concurrent mode failures, incremental compaction, and fragmentation. It also provides examples and explanations of various GC-related log entries.

1. GC Tuning Confessions
Of A Performance
Engineer
Monica Beckwith
monica@codekaram.com
@mon_beck
www.linkedin.com/in/monicabeckwith
JavaOne Conference
Oct. 26th, 2015

2. ©2015 CodeKaram
About Me
• JVM/GC Performance Engineer/Consultant
• Worked at AMD, Sun, Oracle…
• Worked with HotSpot JVM
• JVM heuristics, JIT compiler, GCs:
Parallel(Old) GC, G1 GC, CMS GC
2

3. ©2015 CodeKaram
About Today’s Talk
• A little bit about Performance Engineering
• Insight into Garbage Collectors
• OpenJDK HotSpot GCs
• The Tradeoffs
• GC Algorithms
• Key Topics
• Summary
• GC Tuneables
3

4. Performance
Engineering
4

5. ©2015 CodeKaram
Performance Engineering
5
Requirements
Design
Performance
Requirements & Test
Plan & Development
Implementation
Performance
Analysis

6. ©2015 CodeKaram
Performance Requirements
• Service level agreements (SLAs) for:
• throughput,
• latency and other response time related
metrics E.g. Response time (RT) metrics -
Average (RT), max or worst-case RT, 99th
percentile RT…
6

7. ©2015 CodeKaram
Response Time Metrics
Number of GC
events
Minimum (ms)
System1 37353 7.622
System2 34920 7.258
System3 36270 6.432
System4 40636 7.353
7

8. ©2015 CodeKaram
Number of GC
events
Minimum (ms) Average (ms)
System1 37353 7.622 307.741
System2 34920 7.258 320.778
System3 36270 6.432 321.483
System4 40636 7.353 323.143
8
Response Time Metrics

9. ©2015 CodeKaram
Number of
GC events
Minimum
(ms)
Average
(ms)
99th
Percentile
(ms)
System1 37353 7.622 307.741 940.901
System2 34920 7.258 320.778 1006.607
System3 36270 6.432 321.483 1004.018
System4 40636 7.353 323.143 1041.225
9
Response Time Metrics

10. ©2015 CodeKaram
Number
of GC
events
Minimum
(ms)
Average
(ms)
99th
Percentile
(ms)
Maximum
(ms)
System
1
37353 7.622 307.741 940.901 3131.331
System
2
34920 7.258 320.778 1006.607 2744.588
System
3
36270 6.432 321.483 1004.018 1681.308
System
4
40636 7.353 323.143 1041.225 20699.505
10
Response Time Metrics

11. ©2015 CodeKaram
Average (ms)
99th
Percentile
(ms)
Maximum
(ms)
System1 307.741 940.901 3131.331
System2 320.778 1006.607 2744.588
System3 321.483 1004.018 1681.308
System4 323.143 1041.225 20699.505
5 full GCs and 10 evacuation failures
11
Response Time Metrics

12. Insight into GCs
12

13. ©2015 CodeKaram
Fun Facts!
• GC can NOT eliminate your memory
leaks!
• GC (and heap dump) can provide an
insight into your application.
13

14. ©2015 CodeKaram
Ideal GC?
Maximize Throughput
14

15. ©2015 CodeKaram
Ideal GC?
Maximize Throughput
Minimize Latency
15

16. ©2015 CodeKaram
Ideal GC?
Maximize Throughput
Minimize Latency
Minimize Footprint
16

17. ©2015 CodeKaram
The Reality!
Pick Any Two! :(
17

18. OpenJDK HotSpot
GCs: The TRADE/OFF
18

19. ©2015 CodeKaram
Fun Fact!
Most OpenJDK HotSpot users would like to
increase their (Java) heap space but they
fear full garbage collections.
19

20. ©2015 CodeKaram
The Tradeoff -
• Throughput and latency are the two main drivers
towards refinement of GC algorithms.
20

21. ©2015 CodeKaram
The Throughput Maximizer
21
Maximize
Throughput
Generational
Old
Parallel Work
Young
Concurrent
Threads
Stop-the-
world
Threads

22. ©2015 CodeKaram
Fun Fact!
All GCs in OpenJDK HotSpot are
generational.
22

23. ©2015 CodeKaram
Mr. Latency Sensitive
23
Latency Sensitive
No/Partial
Compaction
Concurrency
Garbage First
Mostly
Concurrent
Mark and Sweep

24. ©2015 CodeKaram
Fun Fact!
All GCs in OpenJDK HotSpot fallback to a
fully compacting stop-the-world garbage
collection called the “full” GC.
Tuning can help avoid or postpone full GCs in
many cases.
24

25. OpenJDK HotSpot
GCs: Algorithms
25

26. ©2015 CodeKaram
The Generational Java Heap
Eden S0 S1 Old Generation
Young Generation
Allocations Survivors
Tenured
26

27. ©2015 CodeKaram
OpenJDK HotSpot
Collectors
*Similar GC
Algorithms
Different GC Algorithms
Always collected in its entirety
27

28. ©2015 CodeKaram
The Serial Collector
Single Threaded
Single Threaded - Entire
Heap Marked, Swept and
Compacted in its entirety
Always collected in its entirety
28

29. ©2015 CodeKaram
Young GC
Thread
Java
Application
Threads
Old GC
Thread
Java
Application
Threads
Java
Application
Threads
The Serial Collector
29

30. ©2015 CodeKaram
The Throughput Collector
Multi-Threaded
Multi-Threaded - Entire
Heap Marked, Swept and
Compacted in its entirety
Always collected in its entirety
30

31. ©2015 CodeKaram
Young GC
Threads
Java
Application
Threads
Old GC
Threads
Java
Application
Threads
Java
Application
Threads
The Throughput Collector
31

32. ©2015 CodeKaram
The CMS Collector
Multi-Threaded
Multi-Threaded - Mostly
Concurrent Marked and
Swept in its entirety
Always collected in its entirety
32

33. ©2015 CodeKaram
The CMS Collector
Young
GC
Threads
CMS
Initial
Mark
Threads
Java
Application
Threads
Young
GC
Threads
CMS
Remark
Threads
Concurrent
CMS Threads
33
Concurrent
CMS Threads
Concurrent
CMS Threads
Java
Application
Threads
Java
Application
Threads
Java
Application
Threads
Java
Application
Threads

34. GC Algorithms - Key
Topics
34

35. 35
What Triggers Full (Fail-Safe)
Collections?

36. Promotion
Failures!
36

37. Promotion Failures In The
Throughput Collector
37

38. ©2015 CodeKaram
The Throughput Collector -
Java Heap
Eden S0 S1 Old Generation
Young Generation
Allocations Survivors
Tenured
38

39. ©2015 CodeKaram
Old Generation
Free Space
Occupied Space
The Throughput Collector -
Contiguous Old Generation
39

40. ©2015 CodeKaram
Old Generation
To-be Promoted Object 1
The Throughput Collector -
Contiguous Old Generation
40

41. ©2015 CodeKaram
The Throughput Collector -
Contiguous Old Generation
41
Old Generation
Free Space
Occupied Space

42. ©2015 CodeKaram
The Throughput Collector -
Contiguous Old Generation
42
Old Generation
To-be Promoted Object 2

43. ©2015 CodeKaram
The Throughput Collector -
Contiguous Old Generation
43
Old Generation
Free Space
Occupied Space

44. ©2015 CodeKaram
The Throughput Collector -
Contiguous Old Generation
44
Old Generation
To-be Promoted Object 3

45. ©2015 CodeKaram
The Throughput Collector -
Contiguous Old Generation
45
Old Generation
Free Space
Occupied Space

46. Promotion Failures &
Concurrent Mode Failures
In The CMS Collector
46

47. ©2015 CodeKaram
The CMS Collector - Old Generation
Maintained By Free Lists
47
Free List
Old Generation
Free Space
Occupied Space

48. ©2015 CodeKaram
To-be Promoted Object 1
48
Old Generation
The CMS Collector - Old Generation
Maintained By Free Lists

49. ©2015 CodeKaram49
Free List
Old Generation
Free Space
Occupied Space
The CMS Collector - Old Generation
Maintained By Free Lists

50. ©2015 CodeKaram50
To-be Promoted Object 2
Old Generation
The CMS Collector - Old Generation
Maintained By Free Lists

51. ©2015 CodeKaram51
Free List
Old Generation
Free Space
Occupied Space
The CMS Collector - Old Generation
Maintained By Free Lists

52. ©2015 CodeKaram
X
52
To-be Promoted Object 3
Old Generation
The CMS Collector - Old Generation
Maintained By Free Lists

53. ©2015 CodeKaram
X
53
To-be Promoted Object 3
Old Generation
The CMS Collector - Old Generation
Maintained By Free Lists

54. ©2015 CodeKaram
X
54
To-be Promoted Object 3
Old Generation
The CMS Collector - Old Generation
Maintained By Free Lists

55. ©2015 CodeKaram
X
55
To-be Promoted Object 3
Old Generation
The CMS Collector - Old Generation
Maintained By Free Lists

56. ©2015 CodeKaram
??
56
To-be Promoted Object 3
Old Generation
The CMS Collector - Old Generation
Maintained By Free Lists

57. ©2015 CodeKaram
Promotion Failure!!
57
To-be Promoted Object 3
Old Generation
The CMS Collector -
Fragmented Old Generation

58. ©2015 CodeKaram
• Your old generation is getting filled before a
concurrent cycle can complete and free up
space.
• Fragmentation has crept in.
• Causes - marking threshold is too high, heap too
small, or high application mutation rate
58
The CMS Collector -
Concurrent Mode Failures

59. Incremental Compaction
In The G1 Collector
59

60. ©2015 CodeKaram
The Garbage First Collector
- Regionalized Heap
Eden
Old Old
Eden
Old
Survivor
Humongous
60

61. ©2015 CodeKaram
The Garbage First Collector
Eden
Old Old
Eden
Old
Surv
ivor
E.g.: Current heap configuration -
61

62. ©2015 CodeKaram
The Garbage First Collector
Eden
Old Old
Eden
Old
Surv
ivor
E.g.: During a young collection -
62

63. ©2015 CodeKaram
The Garbage First Collector
Old Old
Old
E.g.: After a young collection -
Sur
viv
or
Ol
d
63

64. ©2015 CodeKaram
The Garbage First Collector
Old Old
Old
E.g.: Current heap configuration -
Sur
viv
or
Ol
d
Eden Eden
Old
64

65. ©2015 CodeKaram
Old Old
Old
E.g.: Reclamation of a garbage-filled region
during the cleanup phase -
Sur
viv
or
Ol
d
Eden Eden
Old
The Garbage First Collector
65

66. ©2015 CodeKaram
Old Old
Old
E.g.: Reclamation of a garbage-filled region
during the cleanup phase -
Sur
viv
or
Ol
d
Eden Eden
The Garbage First Collector
66

67. ©2015 CodeKaram
Old Old
Old
E.g.: Current heap configuration -
Sur
viv
or
Ol
d
Eden Eden
The Garbage First Collector
67

68. ©2015 CodeKaram
Old Old
Old
E.g.: During a mixed collection -
Sur
viv
or
Ol
d
Eden Eden
The Garbage First Collector
68

69. ©2015 CodeKaram
Old
E.g.: After a mixed collection -
O
l
d
Sur
vivo
r
Old
The Garbage First Collector
69

70. Promotion/Evacuation
Failures In The G1
Collector
70

71. ©2015 CodeKaram
• When there are no more regions available for
survivors or tenured objects, G1 GC encounters
an evacuation failure.
• An evacuation failure is expensive and the usual
pattern is that if you see a couple of evacuation
failures; full GC could* soon follow.
The Garbage First Collector
- Evacuation Failures
71

72. ©2015 CodeKaram
A heavily tuned JVM command line
may be restricting the G1 GC
ergonomics and adaptability.
Start with just your heap sizes and a
reasonable pause time goal
The Garbage First Collector -
Avoiding Evacuation Failures
72

73. ©2015 CodeKaram
Your live data set + long live
transient data may be too large for
the old generation
Check LDS+ and increase heap to
accommodate everything in the old
generation.
The Garbage First Collector -
Avoiding Evacuation Failures
73

74. ©2015 CodeKaram
Initiating Heap Occupancy Threshold
could be the issue.
Check IHOP and make sure it accommodates
the LDS+.
IHOP threshold too high -> Delayed marking ->
Delayed incremental compaction -> Evacuation
Failures!
The Garbage First Collector -
Avoiding Evacuation Failures
74

75. ©2015 CodeKaram
Marking Cycle could be taking too
long to complete?
Increase concurrent marking threads
Reduce IHOP
The Garbage First Collector -
Avoiding Evacuation Failures
75

76. ©2015 CodeKaram
to-space survivors are the problem?
Increase the G1ReservePercent, if to-space
survivors are triggering the evacuation
failures!
The Garbage First Collector -
Avoiding Evacuation Failures
76

77. ©2015 CodeKaram
fragmentation an issue?
The Garbage First Collector -
Avoiding Evacuation Failures
77

78. Fragmentation In The
G1 Collector
78

79. ©2015 CodeKaram
• G1 GC is designed to “absorb” some
fragmentation.
• Default is 5% of the total Java heap
• Tradeoff so that expensive regions are left out.
G1 Heap Waste Percentage
79

80. ©2015 CodeKaram
G1 Mixed GC (Region)
Liveness Threshold
80
• G1 GC’s old regions are also designed to
“absorb” some fragmentation.
• Default is 85% liveness in a G1 region.
• Tradeoff so that expensive regions are left out.

81. ©2015 CodeKaram
The Garbage First Collector
- Humongous Objects
81
An old generation region
A young generation region

82. ©2015 CodeKaram
The Garbage First Collector
- Humongous Objects
82
Object < 50% of
G1 region size
Object >= 50% of
G1 region size
Object > G1
region size
??

83. ©2015 CodeKaram
The Garbage First Collector
- Humongous Objects
83
Object < 50% of
G1 region size

84. ©2015 CodeKaram
The Garbage First Collector
- Humongous Objects
84
Object >= 50% of
G1 region size

85. ©2015 CodeKaram
The Garbage First Collector
- Humongous Objects
85
Object > G1
region size

86. ©2015 CodeKaram
The Garbage First Collector
- Humongous Objects
86
Object NOT Humongous
Object Humongous
Object Humongous ->
Needs Contiguous Regions
Wasted
Space!

87. ©2015 CodeKaram
Ideally, humongous objects are few in
number and are short lived.
A lot of long-lived humongous objects can
cause evacuation failures since humongous
regions add to the old generation occupancy.
The Garbage First Collector
- Humongous Objects
87

88. G1 GC Logs - Key
Topics
88

89. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
89

90. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
90

91. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
91

92. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
92

93. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
93

94. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
94

95. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
95

96. ©2015 CodeKaram
G1 GC Log
154.431: [GC pause (G1 Evacuation Pause) (young), 0.2584864 secs]
[Parallel Time: 253.2 ms, GC Workers: 8]
[GC Worker Start (ms): Min: 154431.3, Avg: 154431.4, Max: 154431.5, Diff: 0.1]
[Ext Root Scanning (ms): Min: 0.1, Avg: 0.2, Max: 0.3, Diff: 0.1, Sum: 1.4]
[Update RS (ms): Min: 3.3, Avg: 3.5, Max: 3.8, Diff: 0.6, Sum: 28.2]
[Processed Buffers: Min: 3, Avg: 3.5, Max: 5, Diff: 2, Sum: 28]
[Scan RS (ms): Min: 46.1, Avg: 46.4, Max: 46.7, Diff: 0.6, Sum: 371.2]
[Code Root Scanning (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[Object Copy (ms): Min: 202.7, Avg: 202.8, Max: 202.9, Diff: 0.3, Sum: 1622.4]
[Termination (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.5]
[GC Worker Other (ms): Min: 0.0, Avg: 0.1, Max: 0.1, Diff: 0.1, Sum: 0.6]
[GC Worker Total (ms): Min: 253.0, Avg: 253.1, Max: 253.1, Diff: 0.1, Sum: 2024.7]
[GC Worker End (ms): Min: 154684.5, Avg: 154684.5, Max: 154684.5, Diff: 0.1]
[Code Root Fixup: 0.1 ms]
[Code Root Purge: 0.0 ms]
[Clear CT: 0.7 ms]
[Other: 4.4 ms]
[Choose CSet: 0.0 ms]
[Ref Proc: 0.3 ms]
[Ref Enq: 0.0 ms]
[Redirty Cards: 0.3 ms]
[Humongous Reclaim: 0.0 ms]
[Free CSet: 3.2 ms]
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors: 148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Times: user=1.72 sys=0.14, real=0.26 secs]
96

97. ©2015 CodeKaram
Generation Sizing
[Eden: 4972.0M(4972.0M)->0.0B(4916.0M) Survivors:
148.0M->204.0M Heap: 5295.8M(10.0G)->379.4M(10.0G)]
[Eden: Occupancy before GC(Eden size before
GC)->Occupancy after GC(Eden size after GC)
Survivors: Size before GC->Size after GC Heap:
Occupancy before GC(Heap size before GC)-
>Occupancy after GC(Heap size after GC)]
97

98. ©2015 CodeKaram
Heap Information Plot
98
OccupancyinMBs
0
7500
15000
22500
30000
TimeStamps
2500 3750 5000 6250 7500 8750 10000 11250 12500
Eden Occupancy Before GC Eden Size After GC
Survivor Size After GC Old Generation Occupancy After GC
Heap Occupancy Before GC Heap Size

99. ©2015 CodeKaram
Scaling: GC Times vs Sys Times
[Times: user=1.72 sys=0.14, real=0.26 secs]
Scaling: user time/real time = 6.6
99

100. ©2015 CodeKaram
Scaling: High Sys Times
100
Swapping?
IO?
Transparent huge
pages enabled??*
Sys memory
issues?
??

101. ©2015 CodeKaram
Reference Processing Times
[Ref Proc: 0.3 ms]
Check for high time spent in ‘Ref Proc’.
Also, check your Remark pause times:
9.972: [GC remark 9.972: [Finalize Marking, 0.0007865 secs]
9.973: [GC ref-proc, 0.0027669 secs] 9.976: [Unloading,
0.0075832 secs], 0.0116215 secs]
If Remark pauses are high or increasing and if ‘ref-
proc’ is the major contributor - use: -XX:
+ParallelRefProcEnabled
101

102. ©2015 CodeKaram
GC Overhead vs Elapsed
Time
Overhead is an indication of the frequency of
stop the world GC events.
The more frequent the GC events - The more
likely it is to negatively impact application
throughput
GC Elapsed Time indicated the amount of time it
takes to execute stop the world GC events
The higher the GC elapsed time - the lower the
application responsiveness due to the GC
induced latencies
102

103. Summary
103

104. ©2015 CodeKaram
Most Allocations Eden Space
Eden Full? Start Young Collection: Keep Allocating :)
Objects Aged in Survivor Space? Promote: Keep Aging :)
Fast Path
Promotions
Fast Path
Old Generation
CMS promotes to fitting free space out of a free list.
What have we learned so
far?
104

105. ©2015 CodeKaram
GC Tuneables - The
Throughput Collector
Goal:
Only promote objects after you have hazed them
appropriately
aged
Tunables:
Everything related to aging objects and
generation sizing -
NewRatio, (Max)NewSize, SurvivorRatio,
(Max)TenuringThreshold
105

106. ©2015 CodeKaram
GC Tuneables - The
Throughput Collector
Things to remember -
• Applications with steady behavior rarely need
AdaptiveSizePolicy to be enabled.
• Overflow gets promoted into the old generation
• Provide larger survivor spaces for transient data.
• In most cases, young generation sizing has the most effect
on throughput
• Size the young generation to maintain the GC overhead to
less than 5%.
106

107. ©2015 CodeKaram
GC Tuneables - The CMS
Collector
Goal:
Only promote objects after you have hazed them
appropriately
aged
Tunables:
Everything related to aging objects and young
generation sizing still applies here.
The concurrent thread counts and marking
threshold are addition tunables for CMS
107

108. ©2015 CodeKaram
GC Tuneables - The CMS
Collector
Things to remember -
• Premature promotions are very expensive in CMS and could lead to
fragmentation
• You can reduce the CMS cycle duration by adding more concurrent
threads: ConcGCThreads.
• Remember that this will increase the concurrent overhead.
• You can manually tune the marking threshold (adaptive by default)
• CMSInitiatingOccupancyFraction & UseCMSInitiatingOccupancyOnly
will help fix the marking threshold.
• Note: The threshold is expressed as a percentage of the old generation
occupancy
108

109. ©2015 CodeKaram
GC Tuneables - The G1
Collector
Goal:
Get the GC ergonomics to work for you and
know the defaults
Tunables:
• Pause time goal, heap size, max and min nursery,
concurrent and parallel threads
• The marking threshold, number of mixed GCs
after marking, liveness threshold for the old
regions, garbage toleration threshold, max old
regions to be collected per mixed collection
109

110. ©2015 CodeKaram
GC Tuneables - The G1
Collector
Things to remember -
• Know your defaults!
• Understand your G1HeapRegionSize - It could be any factor of
two from 1MB to 32MB. G1 strives for 2048 regions.
• Fixing the nursery size (using Xmn) will meddle with the GC
ergonomics/adaptiveness.
• Don’t set really aggressive pause time goals - this will increase the
GC overhead.
• Spend time taming your mixed GCs - mixed GCs are incremental
collections
110

111. ©2015 CodeKaram
GC Tuneables - The G1
Collector
Things to remember -
• Taming mixed GCs:
• Adjust the marking cycle according to you live data set.
• Adjust you liveness threshold - this is the live occupancy threshold
per region. Any region with liveness beyond this threshold will not
be included in a mixed collection.
• Adjust your garbage toleration threshold - helps G1 not get too
aggressive with mixed collections
• Distribute mixed GC pauses over a number of mixed collections -
adjust your mixed GC count target and change your max old region
threshold percent so that you can limit the old regions per collection
111

112. ©2015 CodeKaram
Further Reading
112

113. ©2015 CodeKaram
Further Reading
• Jon Masa’s blog: https://blogs.oracle.com/
jonthecollector/entry/our_collectors
• A few of my articles on InfoQ: http://
www.infoq.com/author/Monica-Beckwith
• Presentations: http://www.slideshare.net/
MonicaBeckwith
• Mail archives on hotspot-gc-use@openjdk.java.net
& hotspot-gc-dev@openjdk.java.net
113

114. Appendix
114

115. ©2015 CodeKaram
Performance Analysis
• Monitoring: System Under Load
• Utilization - CPU, IO, Sys/ Kernel, Memory bandwidth, Java
heap, …
• Lock statistics
• Analyzing:
• Utilization and time spent - GC logs, CPU, memory and
application logs
• Profiling:
• Application, System, Memory - Java Heap.
115

116. ©2015 CodeKaram
JVM Performance
Engineering
Java/JVM performance engineering includes the
study, analysis and tuning of the Just-in-time (JIT)
compiler, the Garbage Collector (GC) and many a
times tuning related to the Java Development Kit
(JDK).
116

117. ©2015 CodeKaram
GC Performance
Engineering
• Monitor the JVM - Visual VM
• Monitor and collect GC information - Visual GC
(online), GC logs (offline)
• Develop scripts to process GC logs; use GC
Histo and JFreeCharts to plot your GC logs or
use specialized tools/ log analyzers that
serves your purpose.
117

118. Summary
118

119. ©2015 CodeKaram
What have we learned so far? -
Young Generation & Collections
• Young generation is always collected in its entirety.
• All 3 server GCs discussed earlier follow similar
mechanism for young collection.
• The young collections achieve reclamation via
compaction and copying of live objects.
• There are a lot of options for sizing the Eden and
Survivor space optimally and many GCs also have
adaptive sizing and GC ergonomics for young
generation collections.
119

120. ©2015 CodeKaram
All 3 server GCs vary in the way they collect the old generation:
• For ParallelOld GC, the old generation is reclaimed and
compacted in its entirety
• Luckily, the compaction cost is distributed amongst parallel
garbage collector worker threads.
• Unluckily, the compaction cost depends a lot on the make of
the live data set since at every compaction, the GC is moving
live data around.
• No tuning options other than the generation size adjustment
and age threshold for promotion.
120
What have we learned so far?
- Old Generation & Collections

121. ©2015 CodeKaram
• For CMS GC, the old generation is (mostly) concurrently marked
and swept. Thus the reclamation of dead objects happen in place
and the space is added to a free list of spaces.
• The marking threshold can be tuned adaptively and manually as
well.
• Luckily, CMS GC doesn’t do compaction, hence reclamation is fast.
• Unluckily, a long running Java application with CMS GC is prone to
fragmentation which will eventually result in promotion failures
which can eventually lead to full compacting garbage collection
and sometimes even concurrent mode failures.
• Full compacting GCs are singled threaded in CMS GC.
What have we learned so far?
- Old Generation & Collections
121

122. ©2015 CodeKaram
• For G1 GC, the old generation regions are (mostly) concurrently marked and
an incremental compacting collection helps with optimizing the old generation
collection.
• Luckily, fragmentation is not “untunable” in G1 GC as it is in CMS GC.
• Unluckily, sometimes, you may still encounter promotion/evacuation failures
when G1 GC runs out of regions to copy live objects. Such an evacuation
failure is expensive and can eventually lead to a full compacting GC.
• Full compacting GCs are singled threaded in G1 GC.
• Appropriate tuning of the old generation space and collection can help
avoid evacuation failures and hence keep full GCs at bay.
• G1 GC has multiple tuning options so that the GC can be adapted to your
application needs.
122
What have we learned so far?
- Old Generation & Collections