Rethinking garbage collection
1 like•363 views
The document discusses advancements in garbage collection, particularly focusing on reference counting (RC) and its optimization for better performance in modern systems. It compares various garbage collection techniques, highlighting a new RC approach that combines its advantages with features of the Immix algorithm to improve efficiency. Ultimately, the new RC method demonstrates competitive performance against traditional methods, achieving faster object collection while retaining locality benefits.
![Mark-Compact [Styger 1967]
Bump allocation + trace + compact
GC Fundamentals
Canonical Garbage Collectors
7
`
Sweep-to-Free
Compact
Evacuate
Mark-Sweep [McCarthy 1960]
Free-list + trace + sweep-to-free
Semi-Space [Cheney 1970]
Bump allocation + trace + evacuate](https://image.slidesharecdn.com/rethinkinggarbagecollection-150526083824-lva1-app6892/85/Rethinking-garbage-collection-7-320.jpg)
![Generational[Ungar 1984]
• Most objects die young
8
Nursery space
Mature space](https://image.slidesharecdn.com/rethinkinggarbagecollection-150526083824-lva1-app6892/85/Rethinking-garbage-collection-8-320.jpg)
![Immix [Blackburn and McKinley 2008]
• Contiguous allocation into regions
– 256B lines and 32KB blocks
– Objects span lines but not blocks
• Simple mark phase
– Mark objects and containing regions
• Free unmarked regions
• Recycled allocation and defragmentation
9
block
line
recyclable linesobject mark line mark](https://image.slidesharecdn.com/rethinkinggarbagecollection-150526083824-lva1-app6892/85/Rethinking-garbage-collection-9-320.jpg)
![Tracing [McCarthy1960]
11
A
D
B
E
C
F
✗ ✗
Roots](https://image.slidesharecdn.com/rethinkinggarbagecollection-150526083824-lva1-app6892/85/Rethinking-garbage-collection-11-320.jpg)
![Reference Counting [Collins 1960]
12
1
1
1
1 2
1
2
0
1
✗
Roots](https://image.slidesharecdn.com/rethinkinggarbagecollection-150526083824-lva1-app6892/85/Rethinking-garbage-collection-12-320.jpg)
Rethinking garbage collection
- 2. Who Am I? • Asst. Prof., Dept. of CSE, BUET • PhD from Australian National University (ANU) • Dissertation title – High Performance Reference Counting and Conservative Garbage Collection • Supervised by – Steve Blackburn (ANU) – Kathryn McKinley (MSR) 2
- 4. The Birth of GC (1960) 4
- 5. Today Garbage collection is ubiquitous • GC algorithms – Tracing and Reference counting • GC implementations – Exact and Conservative ✔ Tracing and Exact in all highly engineered, high performance systems ✘ Reference counting and conservative only in non-performance critical settings 5
- 6. GC Fundamentals Algorithmic Components Allocation Reclamation 6 Identification Bump Allocation Free List ` Tracing (implicit) Reference Counting (explicit) Sweep-to-Free Compact Evacuate 3 1
- 7. Mark-Compact [Styger 1967] Bump allocation + trace + compact GC Fundamentals Canonical Garbage Collectors 7 ` Sweep-to-Free Compact Evacuate Mark-Sweep [McCarthy 1960] Free-list + trace + sweep-to-free Semi-Space [Cheney 1970] Bump allocation + trace + evacuate
- 8. Generational[Ungar 1984] • Most objects die young 8 Nursery space Mature space
- 9. Immix [Blackburn and McKinley 2008] • Contiguous allocation into regions – 256B lines and 32KB blocks – Objects span lines but not blocks • Simple mark phase – Mark objects and containing regions • Free unmarked regions • Recycled allocation and defragmentation 9 block line recyclable linesobject mark line mark
- 10. Down for the Count? Getting Reference Counting Back in the Ring ISMM’12 10
- 12. Reference Counting [Collins 1960] 12 1 1 1 1 2 1 2 0 1 ✗ Roots
- 13. Why Reference Counting? Advantages ✔ Immediacy ✔ Object local ✔ Basic RC is easy Disadvantages ✘ Cycles ✘ Performance 13
- 14. Problem ✔ One of the two fundamental GC algorithms ✔ Many advantages ✘ Neglected by performance-conscious VMs So how much slower is it? Can we get RC back in the ring? 14 30%
- 15. Optimizing RC • Limited bit count – Use just few bits, fix o/f with backup tracing • Elision of new object counts – Only do RC work if object survives the first GC • Born as dead – Avoid free-list work for short lived objects 15
- 16. 16 New RC ≈ MS Optimized RC vs. MS -20% 0% 20% 40% 60% 80% compress jess db javac mtrt jack avrora bloat eclipse fop hsqldb luindex pmd sunflow xalan pjbb2005 geomean faster←Time→slower Old RC New RC
- 17. Summary • Old RC – 30% slower than MS – 40% slower than production • New RC – Limited bit count – Optimization for new objects • Performance – Matches MS – Still 10% slower than production 17 40% 10% TotalTimevProduction < 2012 2012
- 18. Taking Off the Gloves with Reference Counting Immix OOPSLA’13 18
- 19. Why So Slow? 10% 10% -3% TimevProduction 19 Total Mutator GC
- 20. Looking a Little Deeper… 10% 9% 32% 7% 4% 28% -2% -3% -2%-3% -3% 1% MutatorvProduction RC MS SS Immix 20 Time Instructions Retired L1 D Cache Misses
- 21. Looking a Little Deeper… 10% 9% 32% 7% 4% 28% -2% -3% -2%-3% -3% 1% MutatorvProduction RC MS SS Immix 21 Time Instructions Retired L1 D Cache Misses Free List Bump Pointer
- 22. Goal & Challenge • Goal – Object-local collection – Excellent mutator locality – Copying to eliminate fragmentation • Immix provides opportunistic copying ✔ Same mutator locality as contiguous allocator • However, RC is inherently local – References to an object generally unknown – but copying must redirect all references 22
- 23. RC Immix ✔ Combines RC and Immix ✔ Line/block reclamation ✔ Line live object count with object reference count ✔ Exploit Immix’s opportunistic copy ✔ Observe new objects can be copied by first GC ✔ Observe old objects can be copied by backup GC 23
- 24. Total time 3% faster then Gen Immix, +6% worst case, -21% best case 24 -30% -20% -10% 0% 10% 20% 30% 40% compress jess db javac mtrt jack avrora bloat eclipse fop hsqldb jython luindex lusearchfix pmd sunflow xalan pjbb2005 geomean faster←Time→slower RC RC Immix
- 25. Summary • RC Immix – Object-local collection – Excellent mutator locality – Copying with RC • Great performance – Outperforms fastest production • Transforms RC TotalTimevProduction 10% RC 2013 RC Immix -3% 25 Questions?