博士課程での研究まとめ 2023年1月版 / Summary of my research in the PhD course

Transcript

1. ത࢜՝ఔ·ͱΊ
   

   2023೥1݄൛
   ژ౎େֶେֶӃ ৘ใֶݚڀՊ ஌ೳ৘ใֶઐ߈
   
   
   ௶಺ ༎थ
   

   View Slide

2. Ϋϥ΢υܕΞϓϦέʔγϣϯͷߴՄ؍ଌੑ
   

   ʹؔ͢Δݚڀ
   ݚڀ୊໨
   Studies on High Observability of Cloud Applications
   Ϋϥ΢υܕΞϓϦέʔγϣϯͷ؍ଌγεςϜ
   

   ʹ͓͚Δܭଌɾอଘɾղੳͷෛՙʹؔ͢Δݚڀ
   A Study on Loads of Measurement, Storage, and Analysis
   

   in Observation Systems for Cloud Applications
   ީิᶃ
   ީิᶄ
   

   View Slide

3. 3
   ৘ใγεςϜʹ͓͚Δʮ৴པੑʯ
   ෳࡶͳγεςϜʹର͢Δߴස౓ͷมߋͱߴ৴པੑΛཱ྆͢ΔͨΊͷ
   

   ޻ֶతΞϓϩʔν͕ඞཁͱ͞Ε͍ͯΔ
   ݱࡏͷ৘ใγεςϜ͸ɺΠϯλʔωοτΛհͨ͠Ϋϥ΢υίϯϐϡʔςΟϯά
   ʹΑΔఏڙ͕ҰൠతͰ͋Δ
   Ϋϥ΢υ
   Ϧιʔεڞ༗ɺ޿ҬωοτϫʔΫɺҟछι
   ϑτ΢ΣΞ/ϋʔυ΢ΣΞɺͦΕΒͷෳࡶ
   ͳ૬ޓ࡞༻Λ੒͢γεςϜ
   Πϯλʔωοτ
   Ϋϥ΢υܕ
   

   ΞϓϦέʔγϣϯ
   ઌ୺اۀͰ͸ɺ1೔ෳ਺ճҎ্ͷػೳมߋ
   [Humble+, 2018] Accelerate: The Science of Lean Software and DevOps: Building and scaling high performing technology organizations
   [Beyer+, 2016] Site Reliability Engineering: How Google Runs Production Systems
   [Humble+, 2018]
   [Beyer+, 2016]
   

   View Slide

4. 4
   2. ӡ༻ऀʹΑΓએݴ͞Εͨ๬·͠
   ͍ঢ়ଶʹ௥ै͢Δࣗಈ੍ޚ
   3. ӡ༻ऀʹΑΔखಈ੍ޚ
   Ϋϥ΢υͷނোɾো֐ʹର͢Δ੍ޚߏ଄Ϟσϧ
   • ίϯϙʔωϯτ΍௨৴ϨϕϧͰͷ
   

   ނো΍ྼԽରԠ
   
   
   • ఻ૹ੍ޚɾܦ࿏੍ޚɺ෼ࢄ߹ҙͳͲ
   • ܭࢉػΫϥελͷ
   

   ల։ɾࣗಈ৳ॖɾ؅ཧ
   
   
   • OpenStackɺKubernetes
   

   ͳͲͷΦʔέετϨʔλʔ
   • ৴པੑͷ໨ඪ஋Λຬͨ͢Α͏ʹ
   

   ো֐ʹରͯ͠खಈͰରԠ
   
   
   • ༧๷ɾ༧ଌɾݕ஌ɾݪҼ਍அɾ
   

   ճ෮ɾࣄޙ෼ੳɾ࠶ൃ๷ࢭ
   ຊݚڀͰ͸ɺ3.ӡ༻ऀʹΑΔखಈ੍ޚ ʹண໨͢Δ
   Service-level
   Component-level
   System-level
   1. ϓϩτίϧʹ
   

   جͮࣗ͘ಈ੍ޚ
   ʢϑΥʔϧττϨϥϯεʣ
   

   View Slide

5. 5
   ੍ޚͷͨΊͷ಺෦ঢ়ଶͷ؍ଌٕज़
   ඃ؍ଌγεςϜ
   σʔλετΞ
   ӡ༻ऀ
   ؍ଌγεςϜ
   ܭଌث
   ՄࢹԽ
   OSɾΞϓϦέʔγϣϯ
   

   ͷܭ૷ʹΑΓܭଌՄೳ
   ΞϓϦέʔγϣϯ
   ӡ༻σʔλ
   ੍ޚ
   ઐ༻ͷ؍ଌγεςϜ͕ӡ༻σʔλΛܭଌɾอଘɾՄࢹԽ [Hauser+, CLOUD2018]
   ܯใ
   ӡ༻ऀ͕σʔλ͔Β಺෦ঢ়ଶΛཧղ
   

   Ͱ͖ΔΑ͏ʹ͢Δ=Մ؍ଌੑΛ΋ͨͤΔ
   

   View Slide

6. 6
   ӡ༻σʔλࣗಈղੳٕज़ʹΑΔՄ؍ଌੑͷ޲্
   ӡ༻σʔλετΞ ӡ༻ऀ
   ো֐༧ଌ
   [Notaro+, TIST2021]: A Survey of AIOps Methods for Failure Management.
   
   
   [Soldani+, CSUR2022]: Anomaly Detection and Failure Root Cause Analysis in (Micro) Service-Based Cloud Applications: A Survey
   [Notaro+, TIST2021]
   
   
   [Soldani+, CSUR2022]
   ӡ༻σʔλࣗಈղੳث
   ো֐ݕ஌
   ো֐ͷނোՕॴಛఆ
   ʢ౷ܭɾػցֶशʣ
   ਺஋ͷ࣌ܥྻσʔλ
   ωοτϫʔΫ௨৴ͷґଘؔ܎
   [Kim+, PER2013]
   [Chen+, INFOCOM2014]
   [Lin, ICSOC2018]
   [Qiu+, Applied Science2020]
   [Wu+, NOMS2020]
   [Aggarwal+, CLOUD2021]
   ΞϓϦέʔγϣϯίʔυͷ
   

   վมͳ͠Ͱܭ૷Մೳͳӡ༻σʔλ
   ϝτϦΫε
   ίʔϧάϥϑ
   ࣌ؒɾۭؒσʔλΛ
   

   ༻͍ͨղੳख๏
   

   View Slide

7. 7
   ӡ༻σʔλ૿େͷ໰୊
   ΞϓϦέʔγϣϯ ղੳث
   σʔλετΞ
   ղੳෛՙ㽉
   ܭଌෛՙ㽉 อଘෛՙ㽉
   ಛʹো֐ൃੜ࣌ʹ͸
   

   ୹࣌ؒͰͷղੳ͕ٻΊΒΕΔ
   ΞϓϦέʔγϣϯ͕େن໛ԽɾෳࡶԽ͢ΔʹͭΕͯɺඞཁͳӡ༻σʔλ͕૿େ
   
   
   ӡ༻σʔλͷ૿େʹΑΓɺܭଌɾอଘɾղੳෛՙ͕૿େ
   ӡ༻σʔλͷ
   

   ࣍ݩ਺ͷ૿େ
   ӡ༻σʔλͷॻ͖ࠐΈճ਺
   ͱอଘྔͷ૿େ
   ܭଌ࣌ͷσʔλ
   

   ॲཧෛՙͷ૿େ
   

   View Slide

8. 8
   ݚڀ໨త
   ӡ༻σʔλͷ૿େͷࡍʹൃੜ͢Δɺ؍ଌγεςϜʹΑΔ
   ܭଌɾอଘɾղੳͷ֤ෛՙͷݦஶͳ՝୊Λղܾ
   ৚݅ ޿͘ීٴ͢Δٕज़ͷ࿮૊ΈͷதͰ՝୊Λղܾ͢Δ͜ͱʹΑΓɺӡ༻ऀ
   ΁ͷ௥Ճͷӡ༻ෛ୲Λܰݮ͢Δ
   ܭଌෛՙ อଘෛՙ ղੳෛՙ
   ίʔϧάϥϑΛܭଌ͢Δ
   ࡍͷCPUෛՙΛ௿ݮͤ͞
   Δख๏ͷఏҊ
   ϝτϦΫεͷૠೖෛՙͷ
   ௿ݮͱอଘظؒͷ௕ظԽ
   Λཱ྆͢ΔΞʔΩςΫ
   νϟͷఏҊ
   ϝτϦΫε਺ͷ૿େʹର
   ͯ͠ɺߴ଎ʹ໰୊ۭؒΛ
   ॖখ͢Δख๏ΛఏҊ
   ݚڀ՝୊̍ɿ ݚڀ՝୊̎ɿ ݚڀ՝୊̏ɿ
   

   View Slide

9. 9
   ֶज़తߩݙ
   Ϋϥ΢υܕΞϓϦέʔγϣϯͱಉ༷ʹɺมԽͷස౓͕ߴ͘ɺӡ༻ऀ
   ʹΑΔதԝूݖతͳ੍ޚ͕ཁٻ͞ΕΔγεςϜͷ؅ཧख๏ͱͯ͠޿
   ͘Ԡ༻Ͱ͖ΔՄೳੑ͕͋Δ
   ɾΫϥ΢υܕΞϓϦέʔγϣϯ͕ߴՄ؍ଌੑΛ΋ͭͨΊʹඞཁͳܭଌɾอଘɾ
   ղੳͷجຊ֓೦ͱෛՙʹؔ͢Δ՝୊Λମܥతʹ੔ཧ
   
   
   ɾ֤՝୊Λٕज़తʹղܾ͢Δख๏ΛఏҊ͢Δ͜ͱʹΑΓղܾ
   

   View Slide

10. 10
    [ݚڀ՝୊1] ίʔϧάϥϑͷܭଌෛՙ
    ௨৴ͷґଘΛܭଌ͢ΔͨΊʹ͸ɺ௨৴ܦ࿏Λ๣ड͢Δඞཁ͕͋Δ
    ιέοτϨϕϧ
    ύέοτϨϕϧ
    αʔό΍εΠον্Ͱ
    パ
    έοτΛ๣ड͠ɺϔομ಺ͷૹड৴ΞυϨεͱ
    ϙʔτ൪߸͔ΒґଘΛൃݟ͢Δ
    αʔόͷOSΧʔωϧ಺ͰTCP/UDPͷ௨৴ܦ࿏ͷऴ୺ʢιέοτʣʹର͢Δ
    ΠϕϯτΛܭଌ͢Δ
    ୯ҰͷTCP઀ଓ͸ෳ਺ͷύέοτͷϥ΢ϯυτϦοϓͰߏ੒͞ΕΔͨΊɺ
    ιέοτϨϕϧͷ΄͏͕ܭଌෛՙ͕௿͍
    ຊݚڀͰண໨
    

    View Slide

11. Y. Tsubouchi, et al., Low Overhead TCP/UDP Socket-based Tracing for Discovering Network Services Dependencies, Journal of Information Processing 2022.
    [ݚڀ՝୊1] ఏҊख๏
    .
    
    
    .
    
    
    .
    Kernel
    User
    Service
    Socket
    Tracing
    

    Process
    … Event
    Event
    Event
    ετϦʔϛϯά๏(Weave Scope)
    ϑϩʔू໿๏ ([Datadog], [SAC 20])
    ϑϩʔूଋ๏ʢఏҊʣ
    .
    
    
    .
    
    
    .
    Kernel
    Service
    Socket
    Tracing
    

    Process
    .
    
    
    .
    
    
    .
    Event
    Flow
    Event
    Event
    Event
    …
    …
    .
    
    
    .
    
    
    . .
    
    
    .
    
    
    .
    User
    Service
    Socket
    Tracing
    

    Process
    .
    
    
    .
    
    
    .
    ✗ ΧʔωϧˠϢʔβۭؒؒ
    ͷΠϕϯτͷίϐʔίετ
    ✗ TCP઀ଓϨʔτ͕૿Ճ͢Δ
    ͱɺίϐʔίετ͕૿Ճ ෳ਺ͷϑϩʔΛूଋ
    ϑϩʔ= ྆୺ͷΞυϨεͱϙʔτͷ
    ૊ʢλϓϧʣ͕ಉҰͷ௨৴୯Ґ
    Event
    Event …
    …
    Event
    Event
    .
    
    
    .
    
    
    .
    Event
    Event …
    Event
    Event
    .
    
    
    .
    
    
    .
    Ұൠతʹ௨৴͸OSΧʔωϧͷTCP/UDPΛ࢖༻͢Δ͜ͱ
    ʹண໨
    11
    

    View Slide

12. 12
    ɾఏҊख๏͸ɺCPUར༻཰͸2.2%ҎԼɻ
    
    
    ɾϑϩʔ਺ͷ૿େʹରͯ͠ɺϑϩʔूଋʹΑΓɺ
    

    CPUར༻཰Λ௿͘ҡ͍࣋ͯ͠Δ
    [ݚڀ՝୊1] ϑϩʔ਺ͷ૿େʹର͢ΔCPU࢖༻ྔͷมԽ
    ఏҊख๏
    Y. Tsubouchi, et al., Low Overhead TCP/UDP Socket-based Tracing for Discovering Network Services Dependencies, Journal of Information Processing 2022.
    0
    5
    10
    15
    20
    25
    5 10 15 20 25 30 35
    CPU usage / core (%)
    TCP round trips / sec (x103)
    Streaming(client)
    Streaming(server)
    In-Kernel-Aggr(client)
    In-Kernel-Aggr(server)
    In-Kernel-Bundling(client)
    In-Kernel-Bundling(server)
    

    View Slide

13. 13
    [ݚڀ՝୊2] ϝτϦΫεͷอଘෛՙ
    ɾ෺ཧɾ࿦ཧࢿݯ࢖༻ɿCPUɾϝϞϦɾωοτϫʔΫɾσΟεΫɺϓϩηεɾεϨου਺౳
    
    
    ɾཁٻൃߦɿԠ౴஗Ԇ࣌ؒɾεϧʔϓοτɾΤϥʔ਺౳
    ϝτϦΫεͷ
    

    σʔλετΞ
    ΞϓϦέʔγϣϯ
    ϝτϦΫεͷྫ
    5-60ඵ
    

    ִؒ
    300-500೔ఔ౓ͷ
    

    อଘظؒ
    ਺ඦ͔Β਺ेສݸͷ
    

    ܭଌର৅
    

    View Slide

14. 14
    [ݚڀ՝୊2] ϝτϦΫεͷॻ͖ࠐΈճ਺ͱอଘྔͷߴޮ཰Խ
    ϝϞϦ
    

    ϕʔεDB
    σΟεΫ
    

    ϕʔεDB
    σʔλ఺
    

    ૠೖ
    dݸͷσʔλ఺Λ
    

    ஝ੵޙόονॻ͖ࠐΈ
    ఏҊɿೋछDBͷ֊૚Խ
    M
    

    (/s)
    M / d
    

    (/s)
    σΟεΫϕʔε
    
    
    ෼ࢄDB
    ϝϞϦϕʔε
    

    ෼ࢄDB
    ࡧҾߏ଄͕ฏߧ໦
    

    ϝτϦΫε਺nͱ͢Δͱ
    O(log n)ͷܭࢉྔ
    ϝϞϦ
    

    ϕʔεDB
    ϋογϡද O(k)
    ฏߧ໦ O(log n)
    σΟεΫ
    

    ϕʔεDB
    OpenTSDB(HBase)
    
    
    KairosDB(Cassandra)
    
    
    …
    Redis
    

    ࡧҾߏ଄͕ϋογϡද
    

    O(n)ͷܭࢉྔ
    ॻ͖ࠐΈෛՙ͸ϝϞϦϕʔε
    DB͕୲͍ɺσʔλͷ௕ظอଘ
    ͸σΟεΫϕʔεDB͕୲͏
    
    
    ௕ظอଘ޲͖ ௕ظอଘෆ޲͖
    

    View Slide

15. 15
    [ݚڀ՝୊2] ܥྻ਺ͷ૿Ճʹର͢ΔૠೖεϧʔϓοτมԽ
    ɾσΟεΫϕʔεDBͷΈͱൺֱ͠ɺ
    ࠷େͰ3.96ഒͷεϧʔϓοτ
    
    
    ɾεϧʔϓοτͷ௿Լ཰΋վળͨ͠
    0
    20
    40
    60
    80
    100
    100 1K 10K 100k 1M
    0
    20
    40
    60
    Insertion throughput (kilo datapoints / sec)
    Throughput decrease rate (%)
    The number of series
    HeteroTSDB (Proposed)
    KairosDB
    HeteroTSDB (Proposed)
    KairosDB
    ϝϞϦDB → σΟεΫDBͷҠಈεϧʔ
    ϓοτͱϝϞϦDB΁ͷεϧʔϓοτͱ
    ಉఔ౓
    0
    20
    40
    60
    80
    100
    0 300 600 900 1200 1500 1800
    0
    500
    1000
    1500
    2000
    Insertion throughput (kilo datapoints / sec)
    Memory used size (MB)
    Elapsed time (sec)
    Flushed datapoints (/sec)
    Memory used size (MB)
    

    View Slide

16. 16
    [ݚڀ՝୊3] ϝτϦΫεͷղੳෛՙͷ௿ݮͷ՝୊
    ɾো֐ݕ஌ޙͷ୹࣌ؒͰͷނোՕॴಛఆͷͨΊʹɺଟ࣍ݩϝτϦΫεͷ࣍ݩ࡟
    ݮख๏ʹண໨
    จݙ໊ ϝτϦΫε਺ ࣍ݩ࡟ݮʢख๏ʣ ނোՕॴಛఆ
    [PatternMatcher
    
    
    21]
    260K ҟৗݕ஌ʢKSݕఆʣ
    CNNʹΑΔ
    
    
    ҟৗύλʔϯ෼ྨ +
    ҟৗ౓ϥϯΩϯά
    [FluxInfer 20] 12K ҟৗݕ஌ʢࠞ߹ਖ਼ن෼෍ʣ
    ҼՌάϥϑ +
    PageRank
    [FluxRank 19] 541K
    ҟৗݕ஌ʢΧʔωϧີ౓ਪఆʣ
    

    ΫϥελϦϯάʢDBSCANʣ
    ϥϯΩϯάֶश
    ɾ ʮඇܧଓதͷҟৗʯ΍ʮॠؒతͳҟৗʯΛਖ਼ৗͱ෼ྨ͢Δِཅੑ͋Γ
    
    
    ɾ·ͨ͸ɺϝτϦΫεͷछྨ͝ͱͷௐ੔͕ඞཁ
    

    View Slide

17. ࣌ܥྻͷपظͰ͸ͳ͘ɺزԿతͳҟ
    ৗͷಛ௃Λଊ͑Δख๏ͷఏҊ
    17
    [ݚڀ՝୊3] ࣍ݩ࡟ݮ๏ͷϑϨʔϜϫʔΫԽ
    ো֐
    

    ݕ஌
    ނোՕॴ
    

    ಛఆ
    ࣍ݩ࡟ݮ
    ௶಺༎थ΄͔, TSifter: ϚΠΫϩαʔϏεʹ͓͚Δੑೳҟৗͷਝ଎ͳ਍அʹ޲͍ͨ࣌ܥྻσʔλͷ࣍ݩ࡟ݮख๏, Πϯλʔωοτͱӡ༻ٕज़γϯϙδ΢Ϝ࿦จू, 2020೥.
    ఏҊɿނোՕॴಛఆ޲͚ͷ࣍ݩ࡟ݮ๏Λෳ਺ͷϑΣʔζʹ෼ྨ͠ɺطଘͷख๏
    ͷِཅੑͷ՝୊Λղܾ͢Δ
    ϑΣʔζ1ɿΦϑϥΠϯҟৗݕ஌
    ࣌ܥྻͷܗঢ়ͷྨࣅੑʹج͍ͮͨΫ
    ϥελϦϯάΛ࣮ߦ
    
    
    ֤Ϋϥελͷॏ৺ͱͳΔ୅දϝτϦ
    ΫεΛநग़
    ϑΣʔζ̎ɿܗঢ়ྨࣅੑΫϥελϦϯά
    

    View Slide

18. 18
    [ݚڀ՝୊3] ࠶ݱ཰ɺϝτϦΫε࡟ݮੑೳɺߴ଎ੑͷධՁ
    ʮ࣍ݩ࡟ݮʯˠʮނোՕॴಛఆʯͷ౷߹ධՁ
    ɾ࣍ݩ࡟ݮͳ͠ɺطଘͷ࣍ݩ࡟ݮ๏ͱൺֱ͠ɺTop-k ͷಛఆੑೳ͕ʓʓ%޲্
    
    
    ɾϝτϦΫε਺Λ1k ͔Β10kʹ૿Ճͯ͠΋ɺطଘख๏ͱൺֱ͠ɺಛఆੑೳͷ
    ௿Լ཰͕খ͍͞
    σʔλ
    

    ηοτ
    খن໛ɿϝτϦΫε਺ 1k ݸ
    
    
    େن໛ɿϝτϦΫε਺ 10k ݸ
    ʮ࣍ݩ࡟ݮʯͷ෦ҐධՁ
    ɾϑΣʔζ̍ɿఏҊख๏ͷ࠶ݱ཰ʢRecallʣ͕97%
    
    
    ɾϑΣʔζ̎ɿະ੔ཧ
    εϥΠυ࡞੒࣌఺Ͱ͸ɺطଘͷނোՕॴಛఆख
    ๏͕खݩͷσʔληοτͰ͸ඇৗʹ௿͍ಛఆੑ
    ೳΛࣔ͢͜ͱʹ೰·͞Ε͍ͯΔ
    

    View Slide

19. 19
    ݁࿦
    Ϋϥ΢υܕΞϓϦέʔγϣϯͷՄ؍ଌੑΛ޲্ͤ͞Δࡍͷӡ༻σʔλྔͷ૿େ
    ʹର͢ΔܭଌɾอଘɾղੳͷෛՙΛ௿ݮͤ͞Δख๏ΛఏҊͨ͠
    อଘ
    
    
    ෛՙ
    ղੳ
    
    
    ෛՙ
    ܭଌ
    
    
    ෛՙ
    ɾίʔϧάϥϑͷܭଌʹண໨͠ɺLinuxΧʔωϧ಺ͷιέοτͷΠϕϯτΛϑϩʔ୯
    ҐͰऩଋ͢Δܭ૷ํࣜΛఏҊͨ͠
    
    
    ɾಛʹTCP୹໋઀ଓ͕ଟ͍؀ڥͰͷCPUར༻཰Λ௿ݮͤͨ͞
    ɾϝτϦΫε਺ͷ૿େʹରͯ͠ɺϝϞϦϕʔεDBͱσΟεΫϕʔεDBͷࡧҾߏ
    ଄ͷࠩҟʹண໨͠ɺೋछͷDBΛ֊૚Խ͢ΔΞʔΩςΫνϟΛఏҊͨ͠
    
    
    ɾσΟεΫϕʔεDBͷΈͱൺֱ͠ɺ࠷େͰ3.96ഒͷεϧʔϓοτ
    ɾ࣍ݩ਺ʢϝτϦΫε਺ʣͷ૿େʹରͯ͠ɺҟৗݕ஌ͱ࣌ܥྻͷྨࣅ౓ΫϥελϦ
    ϯάͷೋஈ֊ͷ࣍ݩ࡟ݮ๏ΛఏҊͨ͠
    
    
    ɾ࠶ݱ཰Λʓʓ%ɺ˚˚%ͷ࣍ݩ࡟ݮ཰Λୡ੒ͨ͠
    

    View Slide

20. 20
    ത࢜՝ఔͷৼΓฦΓ
    ɾܭըํࣜ̍ɿ͋ΔҰͭͷఏҊͷ࣮ݱʹ޲͚ͯɺෳ਺ͷ࿈ଓͨ͠՝୊Λநग़͠ɺղܾ
    
    
    ɾܭըํࣜ̎ɿ࣮༻্ͷಠཱͨ͠՝୊Λ1ͭͣͭղܾͨ͠ޙʹڞ௨߲ͱҐஔ͚ͮΛ੔ཧ
    
    
    ɾຊݚڀͰ͸ɺํࣜ̎Λ݁Ռతʹ࠾༻
    
    
    ɾૣظͷ࣮༻ԽΛ໨ࢦ͢΄Ͳɺղܾͷ׬શੑ͕ٻΊΒΕΔͷͰɺ՝୊ಉ͕࢜ܨ͕Γʹ͍͘
    ത࢜՝ఔͷݚڀܭը
    ɾ࡞ۀޮ཰
    
    
    ɾจݙͱ࣮ݧ؀ڥΛ՝୊ؒͰڞ༗Ͱ͖ͳ͍ͱɺ࡞ۀྔ͕՝୊਺෼͚ͩ૿େ͢Δ
    
    
    ɾຊݚڀͰ͸ɺશ͘ҟͳΔ࣮ݧ؀ڥΛ3ճߏஙͨ͠
    
    
    ɾݚڀͷෆ࣮֬ੑ΁ͷରԠ
    
    
    ɾ՝୊͕͢ͰʹطଘݚڀͰղܾ͞ΕͨͳͲɺ్தͰ࠳ં͢Δ͜ͱ͕͋Δ
    
    
    ɾຊݚڀͰ͸ɺͲͷ՝୊ʹऔΓ૊Ή͔Ͱ໎͏࣌ؒ͸গͳ͔ͬͨ
    ܭըํࣜ̍ͷ΄͏͕͓ͦΒ͘༗ར
    ܭըํࣜ̎ͷ΄͏͕͓ͦΒ͘༗ར
    

    View Slide

21. 21
    ɾ Y. Tsubouchi, M. Furukawa, R. Matsumoto, Low Overhead TCP/UDP Socket-based Tracing for Discovering
    Network Services Dependencies, Journal of Information Processing (JIP), Vol.30, pp.260-268, 2022೥3݄.
    ͜Ε·Ͱͷݚڀۀ੷: ओͳࠪಡ෇͖࿦จ
    δϟʔφϧ࿦จ
    ࠃࡍձٞ
    ɾ Y. Tsubouchi, M. Furukawa, R. Matsumoto, Transtracer: Socket-Based Tracing of Network Dependencies
    among Processes in Distributed Applications, The 1st IEEE International COMPSAC Workshop on
    Advanced IoT Computing (AIOT 2020), July 2020.
    ࠃ಺γϯϙδ΢Ϝ
    ɾ ௶಺༎थ, ࿬ࡔேਓ, ᖛా݈, দ໦խ޾, খྛོߒ, Ѩ෦ത, দຊ྄հ, HeteroTSDB: ҟछ෼ࢄKVSؒͷࣗಈ֊૚Խ
    ʹΑΔߴੑೳͳ࣌ܥྻσʔλϕʔε, ৘ใॲཧֶձ࿦จࢽ, Vol.62, No.3, pp.818-828, 2021೥3݄.
    ɾ Y. Tsubouchi, A. Wakisaka, K. Hamada, M. Matsuki, H. Abe, R. Matsumoto, HeteroTSDB: An Extensible Time
    Series Database for Automatically Tiering on Heterogeneous Key-Value Stores, The 43rd Annual IEEE
    International Computers, Software & Applications Conference (COMPSAC), pp. 264-269, July 2019.
    ɾ ௶಺༎थ, ௽ాതจ, ݹ઒խେ, TSifter: ϚΠΫϩαʔϏεʹ͓͚Δੑೳҟৗͷਝ଎ͳ਍அʹ޲͍ͨ࣌ܥྻσʔλ
    ͷ࣍ݩ࡟ݮख๏, Πϯλʔωοτͱӡ༻ٕज़γϯϙδ΢Ϝ࿦จू, 2020, 9-16 (2020-11-26), 2020೥12݄.
    ɾ ௶಺༎थ, ҏ໺จ඙, ஔాਅੜ, ࢁ઒૱, ദ໦ַ඙, ഡݪ݉Ұ, ॏෳഉআετϨʔδͷͨΊͷSHA-1
    ܭࢉγεςϜͷSSE໋ྩʹΑΔߴεϧʔϓοτԽ, ిࢠ৘ใ௨৴ֶձ࿦จࢽ D, 96(10), pp.2101-2109 2013೥10݄.
    ʢത࢜࿦จʹؚΊͣʣ
    ɾ ௶಺༎थ, ੨ࢁਅ໵, MeltriaɿϚΠΫϩαʔϏεʹ͓͚Δҟৗݕ஌ɾݪҼ෼ੳͷͨΊͷσʔληοτͷಈతੜ੒
    γεςϜ, Πϯλʔωοτͱӡ༻ٕज़γϯϙδ΢Ϝ࿦จू, 2021, 63-70 (2021-11-18), 2021೥11݄.
    

    View Slide

22. 22
    ͜Ε·Ͱͷݚڀۀ੷ɿͦͷଞ
    ࠃ಺ߨԋ
    ɾ ௶಺༎थ, ௽ాതจ, AI࣌୅ʹ޲͚ͨΫϥ΢υʹ͓͚Δ৴པੑΤϯδχΞϦϯάͷະདྷߏ૝, ϚϧνϝσΟΞɺ
    ෼ࢄɺڠௐͱϞόΠϧʢDICOMO2022ʣγϯϙδ΢Ϝ, 2022೥7݄14೔.
    ɾ ௶಺༎थ, AIOpsݚڀ࿥ʕSREͷͨΊͷγεςϜো֐ͷࣗಈݪҼ਍அ, SRE NEXT 2022 ONLINE, 2022೥5݄.
    ࠃ಺ձٞ࿥ʢࠪಡͳ͠ʣ
    ɾ ྛ༑Ղ, দݪࠀ໻, ࿯๺ݡ, ௶಺༎थ, ϚΠΫϩαʔϏεܕγεςϜͷ؂ࢹʹ͓͚ΔμογϡϘʔυUIઃܭʹىҼ
    ͢Δঢ়گೝࣝ΁ͷӨڹ, No.2022-IOT-56, Vol.38, pp.1-8, 2022೥3݄.
    ɾ দຊ྄հ, ௶಺༎थ, ΫϥΠΞϯτϓϩηεͷݖݶ৘ใʹجͮ͘TCPΛհͨ͠ಁաతͳݖݶ෼཭ํࣜͷઃܭ, ৘
    ใॲཧֶձݚڀใࠂΠϯλʔωοτͱӡ༻ٕज़ʢIOTʣ, No.2020-IOT-49, Vol.11, pp.1-6, 2020೥5݄.
    ɾ ྛ༑Ղ, ҏ੎ా࿇, দݪࠀ໻, ࿯๺ݡ, ௶಺༎थ, দຊ྄հ, ಈతదԠੑΛ࣋ͭ෼ࢄγεςϜΛର৅ͱͨ͠γεςϜ
    ঢ়ଶՄࢹԽख๏ͷݕ౼, ৘ใॲཧֶձݚڀใࠂΠϯλʔωοτͱӡ༻ٕज़ʢIOTʣ, No.2020-IOT-48, Vol.22,
    pp.1-8, 2020೥3݄.
    ɾ ௶಺༎थ, ෼ࢄΞϓϦέʔγϣϯͷ৴པੑ؍ଌٕज़ʹؔ͢Δݚڀ, SRE NEXT 2020 IN TOKYO, 2020೥1݄25೔
    

    View Slide