본문

서브메뉴

Addressing Endpoint-Induced Congestion With Duplicate Acknowledgment
Addressing Endpoint-Induced Congestion With Duplicate Acknowledgment
Addressing Endpoint-Induced Congestion With Duplicate Acknowledgment

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202104743
ISBN  
9798290652191
DDC  
004.62
저자명  
Chong, Timothy.
서명/저자  
Addressing Endpoint-Induced Congestion With Duplicate Acknowledgment
발행사항  
[Sl] : Stanford University, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
115 p
주기사항  
Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
주기사항  
Advisor: Kozyrakis, Christos.
학위논문주기  
Thesis (Ph.D.)--Stanford University, 2025.
초록/해제  
요약The explosive growth of network link bandwidth in modern data centers, now reaching up to 400Gbps in recent hardware, has dramatically outpaced the improvements in host CPU and memory advancements. This widening gap means data can arrive at a receiver far more quickly than it can be processed, creating a significant imbalance that results in endpoint-induced congestion-a new type of congestion occurring at the host NIC or memory when incoming packets overwhelm the receiver's processing capabilities.To cope with these ultra-high network speeds, transport-layer functionalities are increasingly offloaded onto Network Interface Cards (NICs). Technologies such as Remote Direct Memory Access (RDMA) and TCP offload engines facilitate efficient packet processing, acknowledgment handling, and even congestion control directly within NIC hardware. However, this offloading, while beneficial, complicates the detection and proactive management of host-side congestion due to decoupling from the host system.Conventional fabric congestion control algorithms, when directly offloaded to NIC hardware, inherently lose visibility into host-side congestion because acknowledgments (ACKs) are immediately sent upon packet arrival at the NIC rather than after successful DMA transfers into host memory, as would occur in CPU-based networking. Consequently, these algorithms are ill-suited to effectively address endpoint-induced congestion, leading to severe packet loss rates-up to 36% in unicast scenarios and up to 10% per sender in typical incast conditions. Our evaluations reveal frequent cyclic buffer overflows and retransmissions when receiver processing significantly lags behind network speeds, motivating the development of a novel congestion control mechanism explicitly designed for host-induced congestion. For example, standard additive-increase, multiplicative-decrease (AIMD) schemes and even enhanced data center transports (e.g., DCTCP with ECN marking) lack the fine-grained, proactive feedback needed to handle host congestion. Consequently, in NIC-offloaded systems with a slow destination host, these algorithms often overshoot the receiver's capacity, leading to excessive packet loss, and latency spikes of packets.Our evaluations of such legacy approaches show cyclic buffer overflows and retransmission when receiver processing rates significantly lag link rates. This shortcoming motivates a new congestion control mechanism explicitly designed for transport-offloaded data center systems facing host-induced congestion.This dissertation proposes a novel end-to-end congestion control protocol that uses duplicate acknowledgments (DACKs) as an early, explicit signal of host congestion. In contrast to conventional TCP where duplicate ACKs indicate packet loss, here the receiver deliberately sends duplicate ACKs (without advancing its sequence number) to proactively flag that it is overwhelmed. By repurposing duplicate ACKs as a form of negative feedback, the protocol enables tight coordination between sender and receiver. Upon receiving these duplicate ACK signals, the sender promptly slows its sending rate to match the receiver's available processing bandwidth before any buffer overflow or packet drop occurs. Once the receiver catches up and clears its NIC buffer, it resumes sending normal cumulative ACKs with no congestion markings, allowing the sender to cautiously ramp back up. This closed-loop design effectively aligns the sender's transmission rate with the receiver's actual consumption rate in real time, preventing runaway packet bursts, buffer overflows and packet losses.We validate the proposed protocol through a comprehensive simulation-based evaluation. We develop a custom packet-level simulator that models NIC offload architectures and host processing constraints in detail. This environment allows us to simulate realistic data center traffic patterns, including incast workloads with many senders converging on one receiver and scenarios where a host's processing capacity fluctuates over time. We benchmark our mechanism against traditional TCP-style AIMD and an ECN-based host congestion control (HostCC) across these scenarios. Key performance metrics-throughput, packet loss, and latency-are collected to assess how effectively the protocol mitigates endpoint congestion. Our simulation results demonstrate that our congestion control scheme dramatically outperforms existing approaches under host congestion.In a persistent host-overload scenario, our protocol sustained 0% packet loss regardless of NIC buffer size, whereas AIMD and ECN-based schemes suffer continual buffer overflows unless large NIC buffers are provisioned. Under an 8-to-1 incast and all-to-all traffic scenarios with multiple high-speed senders, legacy protocols experienced immense packet drop rate to 10% per sender, while our approach maintained a packet drop rate of 0% with low latency. The scheme also rapidly adapts to dynamic changes in receiver load: as the receiver's processing rate rises or falls, the sender seamlessly adjusts its pace, staying in lock-step without the scattered transmission rates seen in conventional protocols.Overall, by virtually eliminating host-induced packet loss and minimizing latency jitter, the proposed duplicate-ACK mechanism helps transport-offloaded systems better manage the host congestion challenges posed by modern high-speed networks. This research provides a new theoretical framework for end-point congestion control that holistically coordinates network and endpoint resources, charting a path toward more robust data center transport protocols.
일반주제명  
Network interface cards
일반주제명  
Protocol
일반주제명  
Bandwidths
일반주제명  
Traffic congestion
일반주제명  
Computer engineering
일반주제명  
Electrical engineering
키워드  
Modern data centers
키워드  
Receiver's capacity
기타저자  
Stanford University.
기본자료저록  
Dissertations Abstracts International. 87-03B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017358726
■00520260202104743
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798290652191
■035    ▼a(MiAaPQ)AAI32149725
■035    ▼a(MiAaPQ)Stanfordsz161nq7614
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004.62
■1001  ▼aChong,  Timothy.
■24510▼aAddressing  Endpoint-Induced  Congestion  With  Duplicate  Acknowledgment
■260    ▼a[Sl]▼bStanford  University▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a115  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  87-03,  Section:  B.
■500    ▼aAdvisor:  Kozyrakis,  Christos.
■5021  ▼aThesis  (Ph.D.)--Stanford  University,  2025.
■520    ▼aThe  explosive  growth  of  network  link  bandwidth  in  modern  data  centers,  now  reaching  up  to  400Gbps  in  recent  hardware,  has  dramatically  outpaced  the  improvements  in  host  CPU  and  memory  advancements.  This  widening  gap  means  data  can  arrive  at  a  receiver  far  more  quickly  than  it  can  be  processed,  creating  a  significant  imbalance  that  results  in  endpoint-induced  congestion-a  new  type  of  congestion  occurring  at  the  host  NIC  or  memory  when  incoming  packets  overwhelm  the  receiver's  processing  capabilities.To  cope  with  these  ultra-high  network  speeds,  transport-layer  functionalities  are  increasingly  offloaded  onto  Network  Interface  Cards  (NICs).  Technologies  such  as  Remote  Direct  Memory  Access  (RDMA)  and  TCP  offload  engines  facilitate  efficient  packet  processing,  acknowledgment  handling,  and  even  congestion  control  directly  within  NIC  hardware.  However,  this  offloading,  while  beneficial,  complicates  the  detection  and  proactive  management  of  host-side  congestion  due  to  decoupling  from  the  host  system.Conventional  fabric  congestion  control  algorithms,  when  directly  offloaded  to  NIC  hardware,  inherently  lose  visibility  into  host-side  congestion  because  acknowledgments  (ACKs)  are  immediately  sent  upon  packet  arrival  at  the  NIC  rather  than  after  successful  DMA  transfers  into  host  memory,  as  would  occur  in  CPU-based  networking.  Consequently,  these  algorithms  are  ill-suited  to  effectively  address  endpoint-induced  congestion,  leading  to  severe  packet  loss  rates-up  to  36%  in  unicast  scenarios  and  up  to  10%  per  sender  in  typical  incast  conditions.  Our  evaluations  reveal  frequent  cyclic  buffer  overflows  and  retransmissions  when  receiver  processing  significantly  lags  behind  network  speeds,  motivating  the  development  of  a  novel  congestion  control  mechanism  explicitly  designed  for  host-induced  congestion.  For  example,  standard  additive-increase,  multiplicative-decrease  (AIMD)  schemes  and  even  enhanced  data  center  transports  (e.g.,  DCTCP  with  ECN  marking)  lack  the  fine-grained,  proactive  feedback  needed  to  handle  host  congestion.  Consequently,  in  NIC-offloaded  systems  with  a  slow  destination  host,  these  algorithms  often  overshoot  the  receiver's  capacity,  leading  to  excessive  packet  loss,  and  latency  spikes  of  packets.Our  evaluations  of  such  legacy  approaches  show  cyclic  buffer  overflows  and  retransmission  when  receiver  processing  rates  significantly  lag  link  rates.  This  shortcoming  motivates  a  new  congestion  control  mechanism  explicitly  designed  for  transport-offloaded  data  center  systems  facing  host-induced  congestion.This  dissertation  proposes  a  novel  end-to-end  congestion  control  protocol  that  uses  duplicate  acknowledgments  (DACKs)  as  an  early,  explicit  signal  of  host  congestion.  In  contrast  to  conventional  TCP  where  duplicate  ACKs  indicate  packet  loss,  here  the  receiver  deliberately  sends  duplicate  ACKs  (without  advancing  its  sequence  number)  to  proactively  flag  that  it  is  overwhelmed.  By  repurposing  duplicate  ACKs  as  a  form  of  negative  feedback,  the  protocol  enables  tight  coordination  between  sender  and  receiver.  Upon  receiving  these  duplicate  ACK  signals,  the  sender  promptly  slows  its  sending  rate  to  match  the  receiver's  available  processing  bandwidth  before  any  buffer  overflow  or  packet  drop  occurs.  Once  the  receiver  catches  up  and  clears  its  NIC  buffer,  it  resumes  sending  normal  cumulative  ACKs  with  no  congestion  markings,  allowing  the  sender  to  cautiously  ramp  back  up.  This  closed-loop  design  effectively  aligns  the  sender's  transmission  rate  with  the  receiver's  actual  consumption  rate  in  real  time,  preventing  runaway  packet  bursts,  buffer  overflows  and  packet  losses.We  validate  the  proposed  protocol  through  a  comprehensive  simulation-based  evaluation.  We  develop  a  custom  packet-level  simulator  that  models  NIC  offload  architectures  and  host  processing  constraints  in  detail.  This  environment  allows  us  to  simulate  realistic  data  center  traffic  patterns,  including  incast  workloads  with  many  senders  converging  on  one  receiver  and  scenarios  where  a  host's  processing  capacity  fluctuates  over  time.  We  benchmark  our  mechanism  against  traditional  TCP-style  AIMD  and  an  ECN-based  host  congestion  control  (HostCC)  across  these  scenarios.  Key  performance  metrics-throughput,  packet  loss,  and  latency-are  collected  to  assess  how  effectively  the  protocol  mitigates  endpoint  congestion.  Our  simulation  results  demonstrate  that  our  congestion  control  scheme  dramatically  outperforms  existing  approaches  under  host  congestion.In  a  persistent  host-overload  scenario,  our  protocol  sustained  0%  packet  loss  regardless  of  NIC  buffer  size,  whereas  AIMD  and  ECN-based  schemes  suffer  continual  buffer  overflows  unless  large  NIC  buffers  are  provisioned.  Under  an  8-to-1  incast  and  all-to-all  traffic  scenarios  with  multiple  high-speed  senders,  legacy  protocols  experienced  immense  packet  drop  rate  to  10%  per  sender,  while  our  approach  maintained  a  packet  drop  rate  of  0%  with  low  latency.  The  scheme  also  rapidly  adapts  to  dynamic  changes  in  receiver  load:  as  the  receiver's  processing  rate  rises  or  falls,  the  sender  seamlessly  adjusts  its  pace,  staying  in  lock-step  without  the  scattered  transmission  rates  seen  in  conventional  protocols.Overall,  by  virtually  eliminating  host-induced  packet  loss  and  minimizing  latency  jitter,  the  proposed  duplicate-ACK  mechanism  helps  transport-offloaded  systems  better  manage  the  host  congestion  challenges  posed  by  modern  high-speed  networks.  This  research  provides  a  new  theoretical  framework  for  end-point  congestion  control  that  holistically  coordinates  network  and  endpoint  resources,  charting  a  path  toward  more  robust  data  center  transport  protocols.
■590    ▼aSchool  code:  0212.
■650  4▼aNetwork  interface  cards
■650  4▼aProtocol
■650  4▼aBandwidths
■650  4▼aTraffic  congestion
■650  4▼aComputer  engineering
■650  4▼aElectrical  engineering
■653    ▼aModern  data  centers
■653    ▼aReceiver's  capacity
■690    ▼a0544
■690    ▼a0464
■71020▼aStanford  University.
■7730  ▼tDissertations  Abstracts  International▼g87-03B.
■790    ▼a0212
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358726▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF19317 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.