A New LSM-style Garbage Collection Scheme for ZNS SSDs Gunhee Choi, - - PowerPoint PPT Presentation

▶
a new lsm style garbage collection scheme for zns ssds
SMART_READER_LITE
LIVE PREVIEW

A New LSM-style Garbage Collection Scheme for ZNS SSDs Gunhee Choi, - - PowerPoint PPT Presentation

Jul 16, 2023 9 likes •305 views

HotStorage'20 Embedded System Lab. A New LSM-style Garbage Collection Scheme for ZNS SSDs Gunhee Choi, Kwanghee Lee, Myunghoon Oh and Jongmoo Choi from Dankook University Jhuyeong Jhin and Yongseok Oh from SK hynix 12 th USENIX Workshop on

slide-1
SLIDE 1

Embedded System Lab.

HotStorage'20

A New LSM-style Garbage Collection Scheme for ZNS SSDs

  • 2020. 07. 13

Presentation by Choi, Gunhee choi_gunhee@dankook.ac.kr Gunhee Choi, Kwanghee Lee, Myunghoon Oh and Jongmoo Choi from Dankook University Jhuyeong Jhin and Yongseok Oh from SK hynix 12th USENIX Workshop on Hot Topic in Storage and File System (HotStorage 20), 2020

slide-2
SLIDE 2

Embedded System Lab.

Content

HotStorage'20 2

  • 1. Zoned Namespace SSD
  • 2. Motivation
  • 3. LSM-ZGC Design
  • 4. Evaluation
  • 5. Conclusions
  • Appendix
slide-3
SLIDE 3

Embedded System Lab.

HotStorage'20

  • 1. Zoned Namespace SSD

3

Traditional SSD Open-Channel SSD Key-Value SSD Zoned Namespace SSD Optane SSD

  • What are Next Generation SSDs?

vs.

slide-4
SLIDE 4

Embedded System Lab.

HotStorage'20

  • 1. Zoned Namespace SSD

4

Traditional SSD

ü Benefits

  • Better performance and WAF by distributing different workloads into different zones
  • Better isolation (IO Determinism)
  • Reduce DRAM usage and Over-provisioning area in SSDs

LBA space NAND LBA space NAND Zone 1 Zone 2 Zone 3

…

Zoned Namespace SSD

  • What is ZNS SSD?
slide-5
SLIDE 5

Embedded System Lab.

HotStorage'20

  • 1. Zoned Namespace SSD

5

Host Needs to handle zone controls Sequential write constraint Host ZNS SSD Controller Zone

Write Pointer Writing progress direction Unable to write until zone reset

Zone 1 Zone 2 Zone N …

Block device FTL absence

App 1 App 1

  • What are the issues of ZNS SSD?

ü Sequential write constraint: writes need to be conducted in a sequential manner, like the SMR drives. ü Host needs to control zones directly such as zone open, close, reset and zone garbage collection.

slide-6
SLIDE 6

Embedded System Lab.

HotStorage'20

  • 2. Motivation

6

SK Hynix Prototype ZNS SSD

Ref : https://news.skhynix.co.kr/1915

  • How much is the Zone Garbage Collection (hereafter ZGC) overhead?

ü Using real ZNS SSD prototype ü Zone size: 1GB (note that the typical segment size in LFS is 2MB)

slide-7
SLIDE 7

Embedded System Lab.

HotStorage'20

  • 2. Motivation

7

Basic Zone Garbage Collection (Basic_ZGC) Memory Zone Bitmap Zone 0 … Zone 100 …

Step 1. Select a candidate zone (Greedy or CB)

slide-8
SLIDE 8

Embedded System Lab.

HotStorage'20

  • 2. Motivation

8

Basic Zone Garbage Collection Memory Zone Bitmap Zone 0 … Zone 100 …

Step 1. Select a candidate zone (Greedy or CB)

Step 2. Find out valid blocks using a zone bitmap

slide-9
SLIDE 9

Embedded System Lab.

HotStorage'20

  • 2. Motivation

9

Basic Zone Garbage Collection Memory Zone Bitmap Zone 0 … Zone 100 … Step 3. Read valid data in 4KB (or larger) I/O size

Step 1. Select a candidate zone (Greedy or CB)

Step 2. Find out valid blocks using a zone bitmap

slide-10
SLIDE 10

Embedded System Lab.

HotStorage'20

  • 2. Motivation

10

Basic Zone Garbage Collection Memory Zone Bitmap Zone 0 … Zone 100 … Step 3. Read valid data in 4KB (or larger) I/O size

Step 1. Select a candidate zone (Greedy or CB)

Step 2. Find out valid blocks using a zone bitmap Step 4. Write data in 4KB (or larger) I/O size

slide-11
SLIDE 11

Embedded System Lab.

HotStorage'20

  • 2. Motivation

11

Basic Zone Garbage Collection Memory Zone Bitmap Zone 0 … Zone 100 … Step 3. Read valid data in 4KB (or larger) I/O size

Step 1. Select a candidate zone (Greedy or CB)

Step 2. Find out valid blocks using a zone bitmap Step 4. Write data in 4KB (or larger) I/O size Step 5. Reset the selected zone

slide-12
SLIDE 12

Embedded System Lab.

HotStorage'20

  • 2. Motivation

12

  • Zone : 1GB
  • Block : 4KB

Observation 1: Zone garbage collection overhead

slide-13
SLIDE 13

Embedded System Lab.

HotStorage'20

  • 2. Motivation

13

  • Zone : 1GB
  • Block : 4KB

☞Motivation 1: reducing utilization of a candidate zone is indispensable

5 times! 18 times!

Observation 1: Zone garbage collection overhead

slide-14
SLIDE 14

Embedded System Lab.

HotStorage'20

  • 2. Motivation

14

Observation 2: I/O size for Read/Write

  • Another feature of ZNS SSD

ü A zone is, in general, mapped into multiple channels/ways.

  • Then, how about read/write data in a larger I/O size (e.g. 128KB)?
slide-15
SLIDE 15

Embedded System Lab.

HotStorage'20

  • 2. Motivation

15

Observation 2: I/O size for Read/Write

11 Times! ☞Motivation 2: accessing in a larger I/O size is beneficial in ZNS SSDs

slide-16
SLIDE 16

Embedded System Lab.

HotStorage'20

  • 3. LSM-ZGC Design

16

So, Our ideas are 1) Make the utilization of a candidate zone low 2) Access data in a larger I/O size

  • How to access data in a larger I/O size?

ü The coexistence of valid and invalid data makes it difficult ü Read not only valid but also invalid data in a larger I/O size

  • How to make the utilization of a candidate zone low?

ü Traditional hot/cold separation is not applicable in ZNS SSDs since zone is quite big ü Employ the segment concept for finer-grained hot/cold separation

slide-17
SLIDE 17

Embedded System Lab.

HotStorage'20

  • 3. LSM-ZGC Design

17

  • Two management units

ü Zone: for garbage collection vs. Segment: for hot/cold separation ü A zone is divided into multiple segments (1GB vs. 2MB in this study)

  • Segment state and transition rule (refer to our paper for details)

ü New data è C0 ü During ZGC, survived data from C0

§ Data in a high utilized segment ( > thresholdcold): cold è C1C § Others: hot (or unknown) è C1H § Reasoning: spatial locality, also observed in previous studies such as F2FS (FAST’15), Multi-stream (FAST’19), Key-range locality (FAST’20)

ü During ZGC, survived data from C1C or C1H (second survived data)è C2

slide-18
SLIDE 18

Embedded System Lab.

HotStorage'20

  • 3. LSM-ZGC Design

18

Zone 0 Zone 1 Zone 2 Zone N-1

C0_zone

LSM(Log Structured Merge) Zone GC Zone 3 … Zone N Zone Bitmap …

Step 1. Select a candidate zone (or zones, Greedy or CB) C1H_zone C1C_zone

slide-19
SLIDE 19

Embedded System Lab.

HotStorage'20

  • 3. LSM-ZGC Design

19

Zone 0 Zone 1 Zone 2 Zone N-1

C0_zone

…

…

…

2MB 2MB

…

2MB LSM(Log Structured Merge) Zone GC Zone 3 … Zone N Zone Bitmap …

Step 1. Select a candidate zone (or zones, Greedy or CB) Step 2. Read all data in 128KB I/O size C1H_zone C1C_zone

slide-20
SLIDE 20

Embedded System Lab.

HotStorage'20

  • 3. LSM-ZGC Design

20

Zone 0 Zone 1 Zone 2 Zone N-1

C0_zone

…

…

…

2MB 2MB

…

2MB LSM(Log Structured Merge) Zone GC Zone 3 … Zone N Zone Bitmap …

Step 1. Select a candidate zone (or zones, Greedy or CB) Step 2. Read all data in 128KB I/O size Step 3-1. Check valid data Step 3-2. Identify Hot/Cold segment C1H_zone C1C_zone

slide-21
SLIDE 21

Embedded System Lab.

HotStorage'20

  • 3. LSM-ZGC Design

21

Zone 0 Zone 1 Zone 2 Zone N-1

C0_zone

…

…

…

2MB 2MB

…

2MB LSM(Log Structured Merge) Zone GC Zone 3 … Zone N Zone Bitmap …

C1H_zone C1C_zone Step 2. Read all data in 128KB I/O size

… 2MB

Step 3-1. Check valid data Step 4. Merge valid data only according to hot/cold

… 2MB

Hot Segment Cold Segment Step 3-2. Identify Hot/Cold segment Step 1. Select a candidate zone (or zones, Greedy or CB)

slide-22
SLIDE 22

Embedded System Lab.

HotStorage'20

  • 3. LSM-ZGC Design

22

Zone 0 Zone 1 Zone 2 Zone N-1

C0_zone

…

…

…

2MB 2MB

…

2MB LSM(Log Structured Merge) Zone GC Zone 3 … Zone N Zone Bitmap …

Step 1. Select a candidate zone (or zones, Greedy or CB) C1H_zone C1C_zone Step 2. Read all data in 128KB I/O size

… 2MB

Step 4. Merge valid data only according to hot/cold

… 2MB

Hot Segment Cold Segment Step 5. Write data in 128KB I/O size Step 3-1. Check valid data Step 3-2. Identify Hot/Cold segment

slide-23
SLIDE 23

Embedded System Lab.

HotStorage'20

  • 4. Evaluation

23

Experimental environment

  • Intel Core i7 (8 core)
  • 16GB DRAM
  • 1TB ZNS SSD
  • Size of Zone : 1GB

Average of 1.9 times

Garbage collection overhead: uniform update pattern

Max of 2.3 times

slide-24
SLIDE 24

Embedded System Lab.

HotStorage'20

  • 4. Evaluation

24

Garbage collection overhead: skewed update pattern Experimental environment

  • Intel Core i7 (8 core)
  • 16GB DRAM
  • 1TB ZNS SSD
  • Size of Zone : 1GB

Average of 1.4 times Max of 1.6 times

Parameters

  • Workload: 70/30 hot/cold ratio
  • Threaholdcold : 0.8
  • average utilization: x-axis

10 20 30 40 50 0.5 0.6 0.7 0.8 0.9 Garbage collection time (sec) Utilization LSM_ZGC Basic_ZGC

slide-25
SLIDE 25

Embedded System Lab.

HotStorage'20

  • 4. Evaluation

25

Hot/Cold Separation

ü Without hot/cold separation ü With hot/cold separation

Parameters

  • Workload: 70/30 hot/cold ratio
  • Threaholdcold : 0.8
  • Average utilization: 0.6

50 100 150 200 250 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Count

Utilization Garbage Collection Count : 100

50 100 150 200 250 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization Garbage Collection Count : 500

20 40 60 80 100 120 140 160 180 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization

Garbage Collection Count : 900

50 100 150 200 250 300 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count

Utilization Garbage Collection Count : 100

20 40 60 80 100 120 140 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count

Utilization Garbage Collection Count : 500

20 40 60 80 100 120 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count

Utilization Garbage Collection Count : 900

slide-26
SLIDE 26

Embedded System Lab.

HotStorage'20

  • 5. Conclusions

26

  • Our contributions

§ Observation: a zone garbage collection really matters § Proposal: a new LSM-style zone garbage collection scheme § Evaluation: real implementation based results

  • Future work

§ We are currently extending F2FS on our ZNS SSD prototype § Also, evaluating LSM ZGC under diverse workloads with different hot /cold ratio, data size, initial placement and classification policies

slide-27
SLIDE 27

Embedded System Lab.

HotStorage'20

Thank You!

A New LSM-style Garbage Collection Scheme for ZNS SSDs

  • 2020. 07. 13

Presentation by Choi, Gunhee choi_gunhee@dankook.ac.kr Gunhee Choi, Kwanghee Lee, Myunghoon Oh, Jhuyeong Jhin, Yongseok Oh, Jongmoo Choi 12th USENIX Workshop on Hot Topic in Storage and File System (HotStorage 20), 2020

Questions?

slide-28
SLIDE 28

Embedded System Lab.

HotStorage'20

  • 6. Appendix

28

Performance comparison using multi-thread & Scalability

Non-linear Scalability Worker only: 40 With LSM_ZGC : 45 With Basic_ZGC : 53

slide-29
SLIDE 29

Embedded System Lab.

HotStorage'20

  • 6. Appendix

29

Sensitive Analysis: various parameters

ü Effect of thresholdcold (initial utilization: 0.6) ü Effect of initial utilization of a zone (thresholdcold : 0.8)

20 40 60 80 100 120 140 160 180 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization Threshold : 0.6

20 40 60 80 100 120 140 160 180 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization

Threshold : 0.8

20 40 60 80 100 120 140 160 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization Initial Utilization : 0.8

50 100 150 200 250 300 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization Initial Utilization : 0.9

50 100 150 200 250 300 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization Initial Utilization : 0.5

20 40 60 80 100 120 140 160 180 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count Utilization Initial Utilization : 0.6

20 40 60 80 100 120 140 160 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

Count

Utilization Threshold : 0.9