Concurrent GCs - ZGC & Shenandoah

[email protected] Concurrent GCs ZGC & Shenandoah @simonebordet

[email protected] Simone Bordet • @simonebordet • [email protected] • Works @
Webtide ◦ The company behind Jetty and CometD • JVM Tuning Expert 2

Introduction 3

[email protected] Introduction Copy Young Generation Old Generation Parallel Mark Compact
Stop-The-World Concurrent 4

Copy CMS Conc Mark Conc Sweep Stop-The-World Concurrent 5

Copy CMS Conc Mark Conc Sweep Copy G1 Conc Mark Compact Stop-The-World Concurrent 6

Copy CMS Conc Mark Conc Sweep Copy G1 Conc Mark Compact ZGC Conc Mark Conc Compact Shenandoah Conc Mark Conc Compact Stop-The-World Concurrent 7

[email protected] Introduction • Concurrent GCs ◦ GC runs concurrently with
the application • GC races with Application ◦ Marking an object “alive” ◦ Compacting / Moving objects 8

[email protected] Introduction • Concurrent copying example 9 Header a =
1 Header f Region Region

[email protected] Introduction • Garbage Collector compacts object 10 Header a
= 1 Header f Header a = 1 Region Region Region

[email protected] Introduction 11 Header a = 1 Header f Header
a = 1 Region Region Region "From Space" "To Space"

[email protected] Introduction • Application writes concurrently 12 Header a =
3 Header f Header a = 1 Region Region Region

[email protected] Introduction • Garbage Collector updates references 13 Header a
= 3 Header f Header a = 1 Region Region Region LOST WRITE!

[email protected] Introduction • Concurrent GCs store object metadata ◦ E.g.
whether an object has been marked • Concurrent GCs require JIT support • JIT injects code that helps the GC ◦ GC barriers 14

ZGC 15

[email protected] ZGC • Present in OpenJDK 11+ ◦ Available in
AdoptOpenJDK builds ◦ Available in Oracle OpenJDK builds ▪ From https://jdk.java.net • Scalable Low Latency GC • Concurrent Compaction, Single Generation 16

[email protected] ZGC • Only for Linux x86 64-bit ◦ No
compressed pointers ◦ ARM port underway • Region Based ◦ ZPages - similar to G1 regions ▪ Small (2 MiB - object size up to 256 KiB) ▪ Medium (32 MiB - object size up to 4 MiB) ▪ Large (4+ MiB - object size > 4 MiB) 17

[email protected] ZGC STW Mark Start GC Thread App Thread 18
Scan threads stacks Mark object roots

[email protected] ZGC Concurrent Marking GC Thread App Thread 19 Mark
object graph Gather liveness information

[email protected] ZGC GC Thread App Thread 20 Housekeeping STW Mark
End

[email protected] ZGC GC Thread App Thread 21 Weak Reference Processing
Free Memory Pages Unload Classes Prepare Relocation Set Concurrent Processing

[email protected] ZGC GC Thread App Thread 22 Relocate Roots STW
Relocate Start

[email protected] ZGC GC Thread App Thread 23 Relocate Objects (Compact
Heap) Concurrent Relocation

[email protected] ZGC GC Thread App Thread 24 Remapping pointers (Happens
During Next Mark) Concurrent Remapping

[email protected] ZGC • ZGC solution ◦ To avoid races with
the application • Colored Pointers • Load GC barrier 25

[email protected] ZGC • ZGC colored pointers ◦ Color indicates GC
metadata • Check pointer color against GC phase ◦ Wrong color => take action Object address - 44 bits (16 TiB) Unused - 16 bits 64 bits pointer address 4 color bits 26

[email protected] ZGC • ZGC load GC barrier Object f =
obj.field; <load_barrier> 27

obj.field; if (addr_of(f) & wrong_gc_color) { slow_path() } 28

obj.field; <load_barrier> mov 0x10(%rdi), %rsi test %rsi, 0x20(%r15) jne slow_path 29

[email protected] ZGC • ZGC load GC barrier tests for the
right color • Wrong color -> take slow_path ◦ Fix color & Run some action - atomically • The action depends on the GC phase 30

[email protected] ZGC • ZGC Multi-Mapping Virtual Memory 001<addr> 010<addr> 100<addr>
Physical Memory 31

[email protected] ZGC • ZGC Multi-Mapping • RSS shows 3x size
◦ E.g. -Xmx=16G -> RSS~=50G ◦ On Linux, use smem and track PSS • Watch out for OOM Killers in clouds ◦ E.g. AWS 32

[email protected] • Relocation ZGC A E B D C 33
F

[email protected] • Relocation ZGC A E B D F C
C’ D’ MetaData B -> B’ C -> C’ D -> D’ 34 B’

B’ C’ D’ E’ Load Barrier MetaData B -> B’ C -> C’ D -> D’ E -> E’ 35

B’ C’ D’ E’ E” MetaData B -> B’ C -> C’ D -> D’ E -> E’ 36

B’ C’ D’ E’ E” MetaData B -> B’ C -> C’ D -> D’ E -> E’ 37 E -> E”

B’ C’ D’ E’ F’ MetaData B -> B’ C -> C’ D -> D’ E -> E’ F -> F’ 38

[email protected] • Remapping ZGC A B’ C’ D’ E’ F’
39

[email protected] ZGC • References ◦ Per Lidén, Erik Österlund et
al. ▪ https://www.youtube.com/watch?v=7cWiwu7kYkE ▪ https://www.youtube.com/watch?v=kF_r3GE3zOo ◦ Project Wiki ▪ https://wiki.openjdk.java.net/display/zgc/Main ◦ Mailing List ▪ [email protected] 40

ShenandoahGC 41

[email protected] ShenandoahGC • Present in OpenJDK 12+ repository ◦ Available
in AdoptOpenJDK builds ◦ NOT available in Oracle’s OpenJDK builds ◦ Present in RedHat OpenJDK 8, 11+ • Scalable low latency GC • Concurrent Compaction, Single Generation 42

[email protected] ShenandoahGC • Available for x86 32-bit and 64-bit ◦
ARM ports available • Linux, MacOS, Windows ◦ JDK 8, 11 & Latest • Region Based ◦ Derived from G1 43

[email protected] ShenandoahGC STW Mark Start GC Thread App Thread 44
Scan threads stacks Mark object roots

[email protected] ShenandoahGC Concurrent Marking GC Thread App Thread 45 Mark
object graph Gather liveness information

[email protected] ShenandoahGC GC Thread App Thread 46 Weak Reference Processing
Unload Classes Evacuate Roots Housekeeping STW Mark End

[email protected] ShenandoahGC GC Thread App Thread 47 Evacuate Objects (Compact
Heap) Concurrent Evacuation

[email protected] ShenandoahGC GC Thread App Thread 48 Remapping pointers (Happens
During Next Mark) Concurrent Update References

[email protected] ShenandoahGC • ShenandoahGC solution ◦ To avoid races with
the application • Brooks (Forward) Pointers • Load & Store GC Barriers 49

[email protected] ShenandoahGC • HotSpot Object Header ◦ "Word" == 32
bits on i386; 64 bits on x86-64 Mark Word Class Word Field 1 Field 2 Mark Word Class Word Array Length Slot 1 Slot 2 50

[email protected] ShenandoahGC 1.0 • ShenandoahGC 1.0 Class Field1 Field2 Class
Field1 Field2 Mark Mark 51

[email protected] ShenandoahGC 1.0 • ShenandoahGC 1.0 Class Field1 Field2 Class
Field1 Field2 Mark Field1 Field2 Mark Field1 Field2 Fwd Ptr Fwd Ptr Mark Mark Class Class 52

[email protected] ShenandoahGC 1.0 • ShenandoahGC 1.0 • Maintains weak to-space
invariant ◦ Reads from both from-space to-space copies ◦ Writes only to to-space copy 53

[email protected] ShenandoahGC 1.0 • Load GC barrier: dereference forward pointer
Object f = obj.field; <load_barrier> 54

[email protected] ShenandoahGC • Load GC barrier: dereference forward pointer Object
f = obj.field; f = deref(addr_of(f) - 8); 55

[email protected] ShenandoahGC 1.0 • Load GC barrier: dereference forward pointer
Object f = obj.field; <load_barrier> mov 0x10(%rdi), %rsi mov -0x08(%rsi), %rsi 56

[email protected] ShenandoahGC • Store GC barrier ◦ Runs some action
depending on GC phase obj.f = o; <store_barrier> 57

depending on GC phase obj.f = o; if (in_evac_phase && in_collection_set(obj) && !is_forwarded(obj)) slow_path(); 58

depending on GC phase obj.f = o; mov 0x3d8(%r15), %r11 test %r11, %r11 ... jne <slow_path> 59

[email protected] ShenandoahGC • ShenandoahGC 1.0 Problems • More memory needed
(due to the forward pointer) ◦ Worst case 50%, common case 5-10% • Complicated (exotic) GC barriers ◦ Load & Store GC barriers to maintain invariants 60

[email protected] ShenandoahGC • ShenandoahGC 2.0 Class Field1 Field2 Class Field1
Field2 Mark Mark 61

[email protected] ShenandoahGC • ShenandoahGC 2.0 Class Field1 Field2 Class Field1
Field2 Mark Field1 Field2 Field1 Field2 Fwd Ptr Mark Mark Class Class Mark Field1 Field2 Class From Space To Space 62

[email protected] ShenandoahGC • ShenandoahGC 2.0 • Maintains a strong to-space
invariant ◦ Reads only possible from to-space copy ◦ Writes only possible from to-space copy 63

[email protected] ShenandoahGC 2.0 • Load Barrier (LRB - Load Reference
Barrier) ◦ Checks whether there may be forwarded objects ▪ And whether in c-set and whether is forwarded Object f = obj.f; <load_barrier> 64

Barrier) Object f = obj.f; if (in_evac_phase && in_collection_set(obj) && !is_forwarded(obj)) slow_path(); 65

Barrier) Object f = obj.f; test $0x1,0x20(%r15) ... jne <slow_path> 66

[email protected] ShenandoahGC 2.0 • Shenandoah 2.0 • Load and Store
GC barrier are the same! ◦ Big codebase simplification ◦ Improved performance 67

[email protected] • Evacuation ShenandoahGC Class Field1 Field2 Mark 68

[email protected] • Evacuation (GC Copy) ShenandoahGC Class Field1 Field2 Mark
Class Field1 Field2 Mark To Space From Space 69

[email protected] • Evacuation (Application triggers LRB) ShenandoahGC Class Field1 Field2
Mark Class Field1 Field2 Mark Class Field1 Field2 Mark To Space From Space 70

[email protected] • Evacuation (Atomic Fwd Ptr Update) ShenandoahGC Class Field1
Field2 Mark Class Field1 Field2 Mark Class Field1 Field2 Mark To Space From Space 71

[email protected] • Evacuation (Application Wins) ShenandoahGC Class Field1 Field2 Fwd
Ptr Class Field1 Field2 Mark Class Field1 Field2 Mark To Space From Space 72

[email protected] • Evacuation (Application Read/Write) ShenandoahGC Class Field1 Field2 Fwd
Ptr Class Field1 Field2 Mark To Space From Space 73

[email protected] • Update References ShenandoahGC Class Field1 Field2 Fwd Ptr
Class Field1 Field2 Mark To Space From Space 74

[email protected] ShenandoahGC • Shenandoah Heuristics ◦ Adaptive (default) ▪ Maintains
free heap amount ◦ Static ▪ Starts GC when tripping thresholds ◦ Compact ▪ Small footprint ◦ Aggressive ▪ Back to back GCs ◦ Passive ▪ Non concurrent, only Full GCs ◦ Traversal 75

[email protected] ShenandoahGC • References ◦ Project Wiki ▪ https://wiki.openjdk.java.net/display/shenandoah/Main ◦
Aleksey Shipilëv, Roman Kennke et al. ▪ https://www.youtube.com/watch?v=VCeHkcwfF9Q ▪ https://www.youtube.com/watch?v=E1M3hNlhQCg ◦ Mailing List ▪ [email protected] 76

Shenandoah Questions? 77

Conclusions 78

[email protected] Conclusions • Give Concurrent GCs a go • Stuck
with JDK 8? ◦ Use Shenandoah Already using JDK 11+? ◦ ZGC or Shenandoah • Report your feedback! 79

Concurrent GCs - ZGC & Shenandoah

Concurrent GCs - ZGC & Shenandoah

More Decks by Simone Bordet

Other Decks in Programming

Featured

Transcript