SELF- OPTIMIZING DATA GRIDS. Collabora'on Mee'ng with Op'mis, Sept. 2011, Rome

Size: px
Start display at page:

Download "SELF- OPTIMIZING DATA GRIDS. Collabora'on Mee'ng with Op'mis, Sept. 2011, Rome"

Transcription

1 SELF- OPTIMIZING DATA GRIDS Collabora'on Mee'ng with Op'mis, Sept. 2011, Rome

2 Project Goals Develop an open- source middleware for the Cloud: 1. Providing a simple and intui've programming model: hide complexity of distribu'on, elas'city, fault- tolerance 2. Minimizing administra'on and monitoring costs: automate elas'c provisioning based on QoS/cost constraints 3. Minimize opera'onal costs via self- tuning adap'ng consistency mechanisms to maximize efficiency

3 Architecture Overview 31$"456*)01+2$.&) /+#+)01+2$.&) 0"?"$%>"E'&C$%&';&"CC)9;$/%!-$!"#$%$&'()*+%+,-.) J'#M8'-?$-N+8):8"B'9$/%!$ 2=O+8?$5&)*$ 4"NN+&$ #+"&8P$/%!$ 0)-?&)=<?+*$ 6Q+8<B'9$ R&"C+A'&S$ 7+8'9:;<&"=>+$0)-?&)=<?+*$ 7+8'9:;<&"=>+$#?'&";+$#D-?+C$ F27GH2/0$I$J'#$423!127$ F27GH2/0$/3/HKL67$ /0/%1/1!23$4/3/567$ 0"?"$%>"E'&C$ 2NBC)T+&$ 6>"-B8$#8">)9;$ 4"9";+&$ 8.$9'7'$%'%,):) ;<!)%-,$=+=$%)

4 Methodologies explored so far Analy'cal modeling: queuing theory, markov processes stochas'c techniques Machine learning: off- line techniques: Decision Trees, Neural networks, Support Vector Machine on- line techniques (reinforcement learning): UCB algorithm

5 Analytical modeling white box approach: requires detailed knowledge of internal dynamics good extrapola'on power: allow forecas'ng system behavior in unexplored regions of its parameters space minimal learning 'me: basically parameters instan'a'on complex and expensive to design/validate subject to unavoidable approxima'on errors

6 Machine learning Black box approach: observe inputs, context and outputs of a system use sta's'cal methods to iden'fy payerns/rules Good accuracy in already explored regions of the parameters space but poor extrapola'on power Learning 'me grows exponen'ally with number of features: but eventually outperforms analy'cal models (typically!)

7 Hybrid techniques IDEA: get the best of the two worlds Two alterna've approaches so far: 1. Divide- and- conquer: AM for well- specified sub- components ML for sub- components that are: too complex to model explicitly, or whose internal dynamics are only par'ally specified 2. Use AM to ini'alize ML knowledge: reduce learning 'me of ML techniques correct AM using feedback from opera'onal system

8 Self-tuning problems addressed so far Dynamic selec'on and switching between replica'on protocols: total order based replica'on protocols (Case study 1): purely based on Machine Learning techniques Two phase commit vs primary backup (Case study 2): hybrid ML- AM solu'on divide- et- impera GCS op'miza'on: tuning of batching in total order protocols (Case study 3) hybrid ML- AM ML bootstrapped with AM knowledge

9 SELF-TUNING REPLICATION Collabora'on Mee'ng with Op'mis, Sept

10 The search for the holy grail transac'onal replica'on protocols Single master (primary- backup) Mul' master Total order- based 2PC- based Cer'fica'on State machine replica'on Non- vo'ng BFC Vo'ng Collabora'on Mee'ng with Op'mis, Sept

11 No one size fits all Exis'ng solu'ons are op'mized for specific workload/scale scenarios In dynamic environments where both: 1. the workload characteris'cs, and 2. the amount of used resources vary over 'me, self- tuning is the only way to achieve op'mal efficiency Collabora'on Mee'ng with Op'mis, Sept

12 Autonomic adaptation at play low #resources: - minimum costs primary-backup: - low % write: low load on primary auto-scale up: - new nodes hired for read-only requests primary-backup: - low % write: primary stands the load multi-master: - hi % write primary overwhelmed higher scalability auto-scale down: - minimum costs switch back to primary-backup : node processing read-only requests : node processing read&write requests low traffic read-dominated low conflict hi traffic read-dominated low conflict hi traffic write dominated low conflict low traffic read dominated low conflict %&'($ /'$%$#&'()$ %$#&'()$!"#$!"#$%$#&'()$(&*+,*-."+,$ %&'($ /'$(&*4-$ &)2,3,)-$!"#$!"#$(&*4-$ 0'1)$

13 Self-optimizing replication Entails devising solu'ons to 2 keys issues: Allow coexistence/efficient switch among mul'ple replica'on protocols: Avoid blocking transac'on processing during transi'ons Determine the op'mal replica'on strategy given the current (or foreseen) workload characteris'cs: machine learning methods (black box) analy'cal models (white box) hybrid analy'cal/sta's'cal approaches (gray box)

14 Two case studies CerDficaDon Schemes NVC vs VC vs BFC Single vs muld- master 2PC vs PB!"#$%&'()*+,-#"./-0.1+ ("!#'"!#&"!#%"!#$"!" (" "()!!!"" "(!!)!!!"" 2)%*+3)1+3'()+ joint work with M. Couceiro, and L. Rodrigues *+," -.," +," Throughput (Tx/sec) # Nodes PB-low conflict 2PC-low conflict PB-high conflict 2PC-high conflict joint work with D. Didona, S. Peluso and F. Quaglia 2 nd Workshop on Soeware Services, Timisoara, Romania, 6 June

15 Maria Couceiro, Paolo Romano, Luis Rodrigues PolyCert: Polymorphic Self- Op4mizing Replica4on for In- Memory Transac4onal Grids ACM/IFIP/USENIX 12th Interna'onal Middleware Conference (Middleware 2011) TOTAL ORDER BASED CERTIFICATION MECHANISMS

16 Where they fit in the picture Single master (primary- backup) Mul' master Total order- based 2PC- based Cer'fica'on State machine replica'on Non- vo'ng BFC Vo'ng

17 Certification (a.k.a. deferred update) A transac'on is executed en'rely at a single replica: good scalability also in write- intensive workload No coordina'on during transac'on execu'on phase: minimize traffic If the transac'on is ready to commit, coordina'on is required: To ensure serializability To propagate the updates

18 Certification Two transac'ons may update concurrently the same data at different replicas. Coordina'on must detect this situa'on and abort at least one of these transac'ons. Three alterna'ves: Non- vo'ng algorithm Vo'ng algorithm BFC All rely on total order broadcast: - ensure agreement on transac'on serializa'on order - avoid deadlocks - achieve fault- tolerance

19 Classic Replication Protocols Focus on full replica'on protocols Single master (primary- backup) Mul' master Total order based 2PC- based Cer'fica'on State machine replica'on Non- vo'ng BFC Vo'ng

20 Non-voting The transac'on executes locally. When the transac'on is ready to commit, the read and write set are sent to all replicas using total order broadcast Transac'ons are cer'fied in total order. A transac'on may commit if its read set is s'll valid (i.e., no other transac'on has updated the read set).

21 Non-voting R1 Execu'on Transac'on T1 TOB of T1 s read & writeset TOB of T2 s read & writeset R2 Execu'on Transac'on T2 Valida'on&Commit T1 Valida'on&Abort T2 R3 Valida'on&Commit T1 Valida'on&Abort T2 + only validation executed at all replicas: high scalability with write intensive workloads - need to send also readset: often very large!

22 Classic Replication Protocols Focus on full replica'on protocols Single master (primary- backup) Mul' master Total order based 2PC- based Cer'fica'on State machine replica'on Non- vo'ng BFC Vo'ng

23 Voting The transac'on executes locally at replica R When the transac'on is ready to commit, only the write set is sent to all replicas using total order broadcast Commit requests are processed in total order A transac'on may commit if its read set is s'll valid (i.e., no other transac'on has updated the read set): Only R can cerdfy the transacdon! R send the outcome of the transac'on to all replicas

24 Voting R1 Execu'on Transac'on T1 T1 s TOB (ws) T1 s reliable broadcast ( vote ) T1 s valida'on R2 wait for R1 s vote + sends only write-set (much smaller than read-sets normally) - Additional communication phase to disseminate decision (vote)

25 Classic Replication Protocols Single master (primary- backup) Mul' master Total order based 2PC- based Cer'fica'on State machine replica'on Non- vo'ng BFC Vo'ng

26 Bloom Filter Certification (BFC) Bloom filters: space- efficient data structure for test membership queries Probabilis'c answer to Is elem contained in BF? No false nega'ves: A no answer is always correct False posi'ves: A yes answer may be false Compression is a func'on of a (tunable) false posi've rate

27 Bloom Filter Certification (BFC) Key idea: use BF to encode readset and detect intersec'on with writesets of concurrent transac'ons: False posi'ves: addi'onal (determinis'c) abort strongly reduce network traffic: 1% false posi've up to 30x compression

28 BFC vs Voting vs Non-Voting ("!"#$%&'()*+,-#"./-0.1+!#'"!#&"!#%"!#$"!" (" "()!!!"" "(!!)!!!"" 2)%*+3)1+3'()+ *+," -.," +,"

29 PolyCert Polymorphic Self- Op'mizing Cer'fica'on Co- existence of the 3 cer'fica'on schemes Machine- learning techniques to determine the op'mal cer'fica'on strategy per transac'on Logic associated with the on- line choice of the replica'on strategy encapsulated into a generic oracle

30 Architecture!"#$%#&'($#)*+,,)-&#'($**./0!1* Polymorphic Replication Manager 2/3* 453* /3* Replication Protocol Selector Oracle 67&-%-($*!"77* 879"7%%("* :34* ;7#"$7"* replica i

31 Protocol When the transac'on finishes local execu'on: Ask the Oracle which protocol to use. Build a message accordingly. AB- cas t the message.

32 Protocol Upon delivery of an AB- cast message: The message is inserted in a queue with the transac'ons to be cer'fied NVC or BFC: no further processing is done un'l the message reaches the head of the queue VC: If the transac'on does not conflict with others in the queue Local: validate it and send the vote.

33 Protocol Transac'ons are removed from the head of the queue and validated sequen'ally NVC or BFC: each node applies locally the corresponding cer'fica'on algorithm, valida'ng and applying/discarding the write- set. VC: If the vote has been received, act accordingly. Else: Remote: wait for vote. Local: validate transac'on and send the vote.

34 Replication Protocol Selector Oracle Two implementa'ons: Off- line Machine Learning Techniques On- line Reinforcement Learning

35 Off-line Machine Learning Techniques For each transac'on: Predict size of AB message m for the various cer'fica'on schemes Forecast AB latency for each message size. We evaluated several ML approaches: Regression decision trees (best results) Neural networks Support vector machine

36 Regression Decision Trees Define a set of human- readable rules, where each rule: iden'fies a region in the feature space associates with the region a linear func'on of the features Build a piecewise linear approxima'on of a func'on of the features Chooses the branching ayribute such that the resul'ng split maximizes the normalized informa'on gain

37 Neural Networks Inspired by the structure and func'onal aspects of biological neural networks Define weight of connec'ons to minimize average predic'on error across all training data back- propaga'on algorithm

38 Support Vector Machines As a classifier: Iden'fies a set of hyperplanes that have largest distance to the nearest training data points of each class As a func'on approx.: iden'fies the hyperplane that is closer as possible to the set of training data

39 Off-line Machine Learning Techniques Uses up to 53 monitored system ayributes: CPU Memory Network Time- series Requires computa'onal intensive training phase

40 On-line Reinforcement Learning Each replica builds on- line expecta'ons on the rewards of each protocol: no assump'on on rewards distribu'ons Solves the explora'on- exploita'on dilemma: did I test this op'on sufficiently in this scenario?

41 UCB Mul4- armed bandit problem: Each arm of a slot machine is associated with an unknown reward Each round, one arm is played Find the strategy that maximizes the average reward Upper Confidence Bound (UCB): lightweight and provably op'mal solu'on to the bandit problem computes sample average and UCB for each arm UCB captures the degree of uncertainty on the arm s actual reward

42 On-line Reinforcement Learning Dis'nguishes workload scenario solely based on read- set s size exponen'al discre'za'on intervals to minimize training 'me Replicas exchange sta's'cal informa'on periodically to boost learning

43 Results - Bank Benchmark ("!"#$%&'()*+,-#"./-0.1+!#'"!#&"!#%"!#$"!" (" "()!!!"" "(!!)!!!"" 2)%*+3)1+3'()+ *+," -.," +," /0123,-" /4"

44 Results - Bank Benchmark Evolution of Throughput!"#$%&"'%()*(#+,-+./$-0-1.$,23) '#" '!" &#" &!" %#" %!" $#" $!" #" +,-"./01+,-"!"!" &!" (!" )!" $%!" $#!" $*!"!451)*-1.$,2-3)

45 Results - STMBench7 (#%"!"#$%&'()*+,-#"./-0.1+ (#$" ("!#'"!#&"!#%"!#$"!" )*" +," -*." +/01-*."

46 Diego Didona, Sebas'ano Peluso, Paolo Romano, Francesco Quaglia, Luis Rodrigues CASE STUDY 2: PRIMARY-BACKUP <=> 2PC

47 Classic Replication Protocols Single master (primary- backup) Mul' master Total order based 2PC- based Cer'fica'on State machine replica'on Non- vo'ng Vo'ng

48 Single Master Write transac'ons are executed en'rely in a single replica (the primary) If the transac'on aborts, no coordina'on is required. If the transac'on is ready to commit, coordina'on is required to update all the other replicas (backups). Reliable broadcast primi've. Read transac'ons can be executed on backup replicas. No distributed deadlocks No distributed coordinadon during commit Throughput of write txs doesn t scale up with number of nodes

49 Classic Replication Protocols Single master (primary- backup) Mul' master Total order based 2PC- based Cer'fica'on State machine replica'on Non- vo'ng Vo'ng

50 2PC-based replication Transactions attempt to acquire atomically locks at all nodes using two phase commit (2PC) 2PC materializes conflicts among concurrent remote transactions generating: DISTRIBUTED DEADLOCKS + good scalability at low conflict - thrashes at high conflict

51 Performance comparison PB-low conflict 2PC-low conflict PB-high conflict 2PC-high conflict Throughput (Tx/sec) # Nodes

52 Goals Autonomically select the best suited protocol to Minimize transac'ons' service 'me Maximize achievable throughput Elas'cally scale system size Scale up if the system needs more computa'onal power Scale down if the system is oversized

53 Architectural Overview An Autonomic Manager Periodically receives sta's'cs from nodes Aggregates sta's'cs and query an oracle Triggers protocol switch and system scaling The manager resides on one of the system's nodes Communica'on through a dedicated ISPN cache Listeners on the cache for asynchronous communica'on

54 Full Architecture - 2PC

55 Full Architecture - PB

56 Collected Statistics Business logic cost (local transac'on execu'on 'me) Transac'ons arrival rate Put opera'ons per transac'on Percentage of write transac'ons Transport layer latency Conflict degree (more on this later)

57 Key Technical Problem How to forecast Performances of protocol B while running protocol A? Performances of the system with X nodes while running on Y nodes? given that replica'on protocol/scale changes affect: The transac'on conflict probability The transport layer latency

58 Methodology Joint usage of analy'cal modelling and machine learning techniques: analy'cal model of replica'on algorithm dynamics: lock conten'on, distributed deadlock probability message exchange payern machine learning to forecast performance of group communica'on layer: RTT as a func'on of msg size, throughput, #nodes

59 Analytical Model Average transac'on service 'me es'ma'on through the use of an analy'cal model Captures detailed dynamics of replica'on algorithms It is possible to mathema'cally model them, as the algorithms' behaviour is fully known

60 Machine learning techniques Transport layer latency predicted through the use of a sta's'cal model Resource virtualiza'on makes mathema'cal modelling unfeasible: No knowledge of actual load No knowledge of actual physical resources

61 Analytical Model - Overview Focused on modelling data conten'on and replica'on protocols dynamics Key methodologies: Mean Value Analysis & Queuing theory PRO: Good trade- off between performance (of solvers!) and predic'on accuracy CON: Unable to predict distribu'ons, percen'les (useful for instance for SLAs)

62 Analytical Model Contention Probability Conten'on probability depends on Transac'ons arrival rate Read- only vs Update transac'ons Deadlock induced restarts Transac'ons dura'on Business logic (in absence of conten'on) Wai'ng 'me to acquire locks Commit phase (which depends on the replica'on scheme) Data access payern => TRICKY!!! Which items are accessed in what order by transac'ons

63 Analytical Model Data Access Pattern Typical solu'ons Assume a- priori knowledge of access payerns Require non- trivial analysis Probability distribu'on of accesses to data normally assuming very simple distribu'ons Offline: unfeasible for evolving systems Online: costly and complex Hard to deploy in prac'cal seyngs

64 Application Contention Factor Key methodological innova'on: ApplicaDon ContenDon Factor (ACF) Captures probability of intersec'on between datasets accessed by two concurrent transac'ons independently of: concurrency control/replica'on protocol in use number of nodes/threads ac've in the system Derived from measurement of opera'onal system, not computed based on some hypothesized access payern

65 ACF: General idea Assume to be in config s1 (e.g. 2PC, 10 nodes, 3 threads x node) and want to predict performance in config s2 (e.g. PB, 3 nodes, 5 threads x node): 1. while in s1 measure: a) lock dura'on, T hold b) lock request arrival rate, λ c) conflict probability between 2 xact, p conflict 2. derive ACF = p conflict / (T hold * λ) hint: locks modelled as M/G/1 queues 3. ACF can now be used as input of an analy'cal model of the replica'on protocols used in scenario s2

66 Abstracting over applications data access patterns ACF computed based on the lock probability using PB and 2PC across different workload scenarios Application Contention Factor 5e KPR 100KTPC 50KPR 50KTPC 25KPR 25KTPC Application Contention Factor 4e-05 3e-05 2e-05 1e Number of nodes

67 Statistical Model - Overview Based on decision trees Ini'al knowledge base gathered using offline training phase Possibility to periodically update sta's'cal model using data collected online Takes as input a set of metrics gathered in the current system configura'on Outputs the forecast transport layer latency (RTT) for a target configura'on

68 Set of Input Metrics Number of nodes RTT in the current configura'on Size of exchanged messages Throughput of the current configura'on Unknown!!! Guessed using the analy'cal model (more next)

69 Statistical Model Accuracy Correla'on between 0.96 and 0.98 Rela've error between 0.19 and 0.22

70 Models Coupling AnalyDcal model forecasts the ISPN throughput taking as input the RTT in the target configura'on. StaDsDcal model forecasts the RTT taking as input the ISPN throughput in the target configura'on Fixed point solu'on found using recursion

71 Global Model Accuracy PC-est-low conflict 2PC-low conflict 2PC-est-high conflict 2PC-high conflict PB-est-low conflict PB-low conflict Throughput (Tx/sec) # Nodes

72 and now in action! 7000 th.txt u 1: throughput (tx/sec) LOW CONFLICT HIGH CONFLICT time (sec) LOW CONFLICT

73 Future Work Enhance accuracy of analy'cal model in high conten'on scenarios Validate the model also against more complex workload (TPC- C) Assess the suitability of the presented techniques also for elas'c scaling scenarios

74 Paolo Romano and MaYeo Leoney Self- tuning Batching in Total Order Broadcast Protocols via Analy4cal Modelling and Reinforcement Learning IEEE Interna'onal Conference on Compu'ng, Networking and Communica'ons, Network Algorithm & Performance Evalua'on Symposium (ICNC'12), Jan CASE STUDY 3: BATCHING IN TOTAL ORDER BROADCAST PROTOCOLS

75 Sequencer based TOB (STOB) Total order broadcast (TOB) algorithms rely on a special process to ensure total order: P2 m seq sequencer assigns total order seq P3 m TOB(m) message diffusion message ordering

76 Batching in STOB protocols STOB have theore'cally op'mal latency: 2 comm. steps, independently of the number of processes but sequencer becomes the boyleneck at high throughput Batching at the sequencer process: wait for several msgs and order them altogether: amor'ze sequencing cost across mul'ple messages op'mal wai'ng 'me depends on message arrival rate: very effec've at high throughput very bad at low throughput!

77 Analytical model (i) Model sequencing process as a M/M/1 queue: simple queuing model, easily solvable Key equa'on: 'me to sequence a batch of b msgs at arrival rate m: T seq (b,m)=t 1st + (b- 1)/2m + T add (b- 1) T 1st : 'me to sequence a batch of size 1 (b- 1)/2m: avg. wait 'me to build a batch T add (b- 1): overhead for remaining b- 1 messages

78 Analytical model (ii) Using queuing theory arguments we determine the op'mal batching 'me, b *, as a func'on of the arrival rate, m: b (m) = 1, if m< T addσ 2 σ 2mT add σ+ if T addσ m σ 2mT add σ 4σ 2 +2T 2 add σ4 2, 2(σ+2m(T add σ 1)) 2 (2σT add 1) 2 (1+2σT add )σ 2 4σ 2 +2T 2 add σ4 2 <m<m

79 Determining model params To use the model one need to determine two parameters: T 1st & T add Determined using a simple benchmark: 1. find peak throughput w/o batching: m * b=1 2. find peak throughput at max batching level: m * b=max then set: T 1st = 1/m * b=1 T add = 2/m * b=max

80 Model Accuracy Optimal Batching Value Exaustive Manual Tuning Analytical Model Model underes'mates op'mal batching value at medium load Problem: batching underes4ma4on causes system instability! Average Msg. Arrival Rate (msgs/sec)

81 Validation with real traffic Avg Msg. Arrival Rate (msgs/sec) Hour of the day (3 Sept. 2010) Figure 4. Traffic at the FenixEDU system (Sept )

82 Peak period analysis msgs/sec Latency (msec) Hour of the day Ramp- up & ramp- down transi'on through the problema'c areas: - ramp- up is sufficiently short: system struggles, but recovers - ramp- down is longer:

83 What about a pure ML approach? Discre'za'on of the func'on b * =f(m) that outputs the op'mal batching b * given the current message arrival rate m m={10,100,1000,2000,,16000} b={1,2,4,8,,256} Use an instance of UCB with each arrival rate m, having an arm per each batching value b: use UCB to determine the most rewarding arm

84 Pure ML approaches Problem: ML techniques need to explore different solu'ons (batching values) to iden'fy op'mal one: low load: useless addi'onal latency medium- high load: insufficient batching values lead very rapidly to instability and thrashing

85 Combining the two approaches 1. Ini'alize UCB rewards with the predic'ons of the analy'cal model: reduce frequency of obviously wrong explora'ons 2. Let UCB update the ini'al reward values: correct model s predic'on errors exploi'ng feedback from the system

86 Combining the two approaches Latency (msec) Model Model+RL msgs/sec Hour of the day

87 Future work Focus on elas'c- scaling, keeping into account data grids dynamics: consistency costs, transac'on conflicts Study effects of self- tuning mul'ple, mutually dependent layers of the data grid BeYer integra'on with QoS specifica'on APIs

Virtual Synchrony. Jared Cantwell

Virtual Synchrony. Jared Cantwell Virtual Synchrony Jared Cantwell Review Mul7cast Causal and total ordering Consistent Cuts Synchronized clocks Impossibility of consensus Distributed file systems Goal Distributed programming is hard What

More information

A Distributed Data- Parallel Execu3on Framework in the Kepler Scien3fic Workflow System

A Distributed Data- Parallel Execu3on Framework in the Kepler Scien3fic Workflow System A Distributed Data- Parallel Execu3on Framework in the Kepler Scien3fic Workflow System Ilkay Al(ntas and Daniel Crawl San Diego Supercomputer Center UC San Diego Jianwu Wang UMBC WorDS.sdsc.edu Computa3onal

More information

Decision making for autonomous naviga2on. Anoop Aroor Advisor: Susan Epstein CUNY Graduate Center, Computer science

Decision making for autonomous naviga2on. Anoop Aroor Advisor: Susan Epstein CUNY Graduate Center, Computer science Decision making for autonomous naviga2on Anoop Aroor Advisor: Susan Epstein CUNY Graduate Center, Computer science Overview Naviga2on and Mobile robots Decision- making techniques for naviga2on Building

More information

Consistency Rationing in the Cloud: Pay only when it matters

Consistency Rationing in the Cloud: Pay only when it matters Consistency Rationing in the Cloud: Pay only when it matters By Sandeepkrishnan Some of the slides in this presenta4on have been taken from h7p://www.cse.iitb.ac.in./dbms/cs632/ra4oning.ppt 1 Introduc4on:

More information

Using Sequen+al Run+me Distribu+ons for the Parallel Speedup Predic+on of SAT Local Search

Using Sequen+al Run+me Distribu+ons for the Parallel Speedup Predic+on of SAT Local Search Using Sequen+al Run+me Distribu+ons for the Parallel Speedup Predic+on of SAT Local Search Alejandro Arbelaez - CharloBe Truchet - Philippe Codognet JFLI University of Tokyo LINA, UMR 6241 University of

More information

Stacking it Up Experimental Observa6ons on the opera6on of Dual Stack Services

Stacking it Up Experimental Observa6ons on the opera6on of Dual Stack Services Stacking it Up Experimental Observa6ons on the opera6on of Dual Stack Services Geoff Huston, APNIC Labs 1 If working with one protocol has its problems 2 Then just how much damage can we do by joining

More information

Example. You manage a web site, that suddenly becomes wildly popular. Performance starts to degrade. Do you?

Example. You manage a web site, that suddenly becomes wildly popular. Performance starts to degrade. Do you? Scheduling Main Points Scheduling policy: what to do next, when there are mul:ple threads ready to run Or mul:ple packets to send, or web requests to serve, or Defini:ons response :me, throughput, predictability

More information

TerraSwarm. A Machine Learning and Op0miza0on Toolkit for the Swarm. Ilge Akkaya, Shuhei Emoto, Edward A. Lee. University of California, Berkeley

TerraSwarm. A Machine Learning and Op0miza0on Toolkit for the Swarm. Ilge Akkaya, Shuhei Emoto, Edward A. Lee. University of California, Berkeley TerraSwarm A Machine Learning and Op0miza0on Toolkit for the Swarm Ilge Akkaya, Shuhei Emoto, Edward A. Lee University of California, Berkeley TerraSwarm Tools Telecon 17 November 2014 Sponsored by the

More information

Search Engines. Informa1on Retrieval in Prac1ce. Annota1ons by Michael L. Nelson

Search Engines. Informa1on Retrieval in Prac1ce. Annota1ons by Michael L. Nelson Search Engines Informa1on Retrieval in Prac1ce Annota1ons by Michael L. Nelson All slides Addison Wesley, 2008 Evalua1on Evalua1on is key to building effec$ve and efficient search engines measurement usually

More information

CS 61C: Great Ideas in Computer Architecture (Machine Structures) Lecture 32: Pipeline Parallelism 3

CS 61C: Great Ideas in Computer Architecture (Machine Structures) Lecture 32: Pipeline Parallelism 3 CS 61C: Great Ideas in Computer Architecture (Machine Structures) Lecture 32: Pipeline Parallelism 3 Instructor: Dan Garcia inst.eecs.berkeley.edu/~cs61c! Compu@ng in the News At a laboratory in São Paulo,

More information

No compromises: distributed transac2ons with consistency, availability, and performance

No compromises: distributed transac2ons with consistency, availability, and performance No compromises: distributed transac2ons with consistency, availability, and performance Aleksandar Dragojevic, Dushyanth Narayanan, Edmund B. Nigh2ngale, MaDhew Renzelmann, Alex Shamis, Anirudh Badam,

More information

Cloud Computing WSU Dr. Bahman Javadi. School of Computing, Engineering and Mathematics

Cloud Computing WSU Dr. Bahman Javadi. School of Computing, Engineering and Mathematics Cloud Computing Research @ WSU Dr. Bahman Javadi School of Computing, Engineering and Mathematics Research Team and Research Interests Team 4 Academic Staff 5 PhD Students 1 Master Student Resource Scheduling

More information

ECE 1749H: Interconnec1on Networks for Parallel Computer Architectures: Rou1ng. Prof. Natalie Enright Jerger

ECE 1749H: Interconnec1on Networks for Parallel Computer Architectures: Rou1ng. Prof. Natalie Enright Jerger ECE 1749H: Interconnec1on Networks for Parallel Computer Architectures: Rou1ng Prof. Natalie Enright Jerger Announcements Feedback on your project proposals This week Scheduled extended 1 week Next week:

More information

Today s Objec4ves. Data Center. Virtualiza4on Cloud Compu4ng Amazon Web Services. What did you think? 10/23/17. Oct 23, 2017 Sprenkle - CSCI325

Today s Objec4ves. Data Center. Virtualiza4on Cloud Compu4ng Amazon Web Services. What did you think? 10/23/17. Oct 23, 2017 Sprenkle - CSCI325 Today s Objec4ves Virtualiza4on Cloud Compu4ng Amazon Web Services Oct 23, 2017 Sprenkle - CSCI325 1 Data Center What did you think? Oct 23, 2017 Sprenkle - CSCI325 2 1 10/23/17 Oct 23, 2017 Sprenkle -

More information

Machine Learning Crash Course: Part I

Machine Learning Crash Course: Part I Machine Learning Crash Course: Part I Ariel Kleiner August 21, 2012 Machine learning exists at the intersec

More information

Opera&ng Systems ECE344

Opera&ng Systems ECE344 Opera&ng Systems ECE344 Lecture 10: Scheduling Ding Yuan Scheduling Overview In discussing process management and synchroniza&on, we talked about context switching among processes/threads on the ready

More information

MapReduce, Apache Hadoop

MapReduce, Apache Hadoop NDBI040: Big Data Management and NoSQL Databases hp://www.ksi.mff.cuni.cz/ svoboda/courses/2016-1-ndbi040/ Lecture 2 MapReduce, Apache Hadoop Marn Svoboda svoboda@ksi.mff.cuni.cz 11. 10. 2016 Charles University

More information

MapReduce, Apache Hadoop

MapReduce, Apache Hadoop Czech Technical University in Prague, Faculty of Informaon Technology MIE-PDB: Advanced Database Systems hp://www.ksi.mff.cuni.cz/~svoboda/courses/2016-2-mie-pdb/ Lecture 12 MapReduce, Apache Hadoop Marn

More information

About the Course. Reading List. Assignments and Examina5on

About the Course. Reading List. Assignments and Examina5on Uppsala University Department of Linguis5cs and Philology About the Course Introduc5on to machine learning Focus on methods used in NLP Decision trees and nearest neighbor methods Linear models for classifica5on

More information

Cache Coherence in Distributed and Replicated Transactional Memory Systems. Technical Report RT/4/2009

Cache Coherence in Distributed and Replicated Transactional Memory Systems. Technical Report RT/4/2009 Technical Report RT/4/2009 Cache Coherence in Distributed and Replicated Transactional Memory Systems Maria Couceiro INESC-ID/IST maria.couceiro@ist.utl.pt Luis Rodrigues INESC-ID/IST ler@ist.utl.pt Jan

More information

A MAC protocol for Reliable Broadcast Communica7ons in Wireless Network- on- Chip

A MAC protocol for Reliable Broadcast Communica7ons in Wireless Network- on- Chip A MAC protocol for Reliable Broadcast Communica7ons in Wireless Network- on- Chip Sergi Abadal (abadal@ac.upc.edu) Albert Mestres, Josep Torrellas, Eduard Alarcón, and Albert Cabellos- Aparicio UPC and

More information

DD2451 Parallel and Distributed Computing --- FDD3008 Distributed Algorithms

DD2451 Parallel and Distributed Computing --- FDD3008 Distributed Algorithms DD2451 Parallel and Distributed Computing --- FDD3008 Distributed Algorithms Lecture 8 Leader Election Mads Dam Autumn/Winter 2011 Previously... Consensus for message passing concurrency Crash failures,

More information

CSE 473: Ar+ficial Intelligence

CSE 473: Ar+ficial Intelligence CSE 473: Ar+ficial Intelligence Search Instructor: Luke Ze=lemoyer University of Washington [These slides were adapted from Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All CS188 materials

More information

Scalability in a Real-Time Decision Platform

Scalability in a Real-Time Decision Platform Scalability in a Real-Time Decision Platform Kenny Shi Manager Software Development ebay Inc. A Typical Fraudulent Lis3ng fraud detec3on architecture sync vs. async applica3on publish messaging bus request

More information

SEDA An architecture for Well Condi6oned, scalable Internet Services

SEDA An architecture for Well Condi6oned, scalable Internet Services SEDA An architecture for Well Condi6oned, scalable Internet Services Ma= Welsh, David Culler, and Eric Brewer University of California, Berkeley Symposium on Operating Systems Principles (SOSP), October

More information

Starchart*: GPU Program Power/Performance Op7miza7on Using Regression Trees

Starchart*: GPU Program Power/Performance Op7miza7on Using Regression Trees Starchart*: GPU Program Power/Performance Op7miza7on Using Regression Trees Wenhao Jia, Princeton University Kelly A. Shaw, University of Richmond Margaret Martonosi, Princeton University *Sta7s7cal Tuning

More information

Reminder from last ;me

Reminder from last ;me Concurrent systems Lecture 5: Concurrency without shared data; transac;ons Dr Robert N. M. Watson 1 Reminder from last ;me Liveness proper;es Deadlock (requirements; resource alloca;on graphs; detec;on;

More information

Stages of (Batch) Machine Learning

Stages of (Batch) Machine Learning Evalua&on Stages of (Batch) Machine Learning Given: labeled training data X, Y = {hx i,y i i} n i=1 Assumes each x i D(X ) with y i = f target (x i ) Train the model: model ß classifier.train(x, Y ) x

More information

What If Everyone Did It? Geoff Huston APNIC Labs

What If Everyone Did It? Geoff Huston APNIC Labs What If Everyone Did It? Geoff Huston APNIC Labs DNS Security Se#ng the AD bit in a recursive resolver response seems like a rather unimpressive way of conveying a posi;ve security outcome, and in the

More information

Vulnerability Analysis (III): Sta8c Analysis

Vulnerability Analysis (III): Sta8c Analysis Computer Security Course. Vulnerability Analysis (III): Sta8c Analysis Slide credit: Vijay D Silva 1 Efficiency of Symbolic Execu8on 2 A Sta8c Analysis Analogy 3 Syntac8c Analysis 4 Seman8cs- Based Analysis

More information

CS 188: Ar)ficial Intelligence

CS 188: Ar)ficial Intelligence CS 188: Ar)ficial Intelligence Search Instructors: Pieter Abbeel & Anca Dragan University of California, Berkeley [These slides were created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley

More information

Database Machine Administration v/s Database Administration: Similarities and Differences

Database Machine Administration v/s Database Administration: Similarities and Differences Database Machine Administration v/s Database Administration: Similarities and Differences IOUG Exadata Virtual Conference Vivek Puri Manager Database Administration & Engineered Systems The Sherwin-Williams

More information

Chunking: An Empirical Evalua3on of So7ware Architecture (?)

Chunking: An Empirical Evalua3on of So7ware Architecture (?) Chunking: An Empirical Evalua3on of So7ware Architecture (?) Rachana Koneru David M. Weiss Iowa State University weiss@iastate.edu rachana.koneru@gmail.com With participation by Audris Mockus, Jeff St.

More information

SELF-TUNING HTM. Paolo Romano

SELF-TUNING HTM. Paolo Romano SELF-TUNING HTM Paolo Romano 2 Based on ICAC 14 paper N. Diegues and Paolo Romano Self-Tuning Intel Transactional Synchronization Extensions 11 th USENIX International Conference on Autonomic Computing

More information

ECSE 425 Lecture 25: Mul1- threading

ECSE 425 Lecture 25: Mul1- threading ECSE 425 Lecture 25: Mul1- threading H&P Chapter 3 Last Time Theore1cal and prac1cal limits of ILP Instruc1on window Branch predic1on Register renaming 2 Today Mul1- threading Chapter 3.5 Summary of ILP:

More information

ECS 165B: Database System Implementa6on Lecture 14

ECS 165B: Database System Implementa6on Lecture 14 ECS 165B: Database System Implementa6on Lecture 14 UC Davis April 28, 2010 Acknowledgements: por6ons based on slides by Raghu Ramakrishnan and Johannes Gehrke, as well as slides by Zack Ives. Class Agenda

More information

Autonomic Mul,- Agents Security System for mul,- layered distributed architectures. Chris,an Contreras

Autonomic Mul,- Agents Security System for mul,- layered distributed architectures. Chris,an Contreras Autonomic Mul,- s Security System for mul,- layered distributed architectures Chris,an Contreras Agenda Introduc,on Mul,- layered distributed architecture Autonomic compu,ng system Mul,- System (MAS) Autonomic

More information

Deformable Part Models

Deformable Part Models Deformable Part Models References: Felzenszwalb, Girshick, McAllester and Ramanan, Object Detec@on with Discrimina@vely Trained Part Based Models, PAMI 2010 Code available at hkp://www.cs.berkeley.edu/~rbg/latent/

More information

Storwize in IT Environments Market Overview

Storwize in IT Environments Market Overview Storwize in IT Environments Market Overview Topic Challenges in Tradi,onal IT Environment Types of informa,on Storage systems required Storage for private clouds where tradi,onal IT is involved Storwize

More information

CLOUD SERVICES. Cloud Value Assessment.

CLOUD SERVICES. Cloud Value Assessment. CLOUD SERVICES Cloud Value Assessment www.cloudcomrade.com Comrade a companion who shares one's ac8vi8es or is a fellow member of an organiza8on 2 Today s Agenda! Why Companies Should Consider Moving Business

More information

D3.3: Performance forecasting models.

D3.3: Performance forecasting models. Cloud-TM Specific Targeted Research Project (STReP) Contract no. 257784 D3.3: Performance forecasting models. Date of preparation: 30 May 2012 Start date of project: 1 June 2010 Duration: 36 Months Contributors

More information

OPTIMAL ROUTING VS. ROUTE REFLECTOR VNF - RECONCILE THE FIRE WITH WATER

OPTIMAL ROUTING VS. ROUTE REFLECTOR VNF - RECONCILE THE FIRE WITH WATER OPTIMAL ROUTING VS. ROUTE REFLECTOR VNF - RECONCILE THE FIRE WITH WATER Rafal Jan Szarecki #JNCIE136 Solu9on Architect, Juniper Networks. AGENDA Route Reflector VNF - goals Route Reflector challenges and

More information

Transactional Auto Scaler: Elastic Scaling of Replicated In-Memory Transactional Data Grids 1

Transactional Auto Scaler: Elastic Scaling of Replicated In-Memory Transactional Data Grids 1 Technical Report RT/12/2014 Transactional Auto Scaler: Elastic Scaling of Replicated In-Memory Transactional Data Grids 1 Diego Didona, Paolo Romano INESC-ID / Instituto Superior Técnico, Universidade

More information

Bioinforma)cs Resources - NoSQL -

Bioinforma)cs Resources - NoSQL - Bioinforma)cs Resources - NoSQL - Lecture & Exercises Prof. B. Rost, Dr. L. Richter, J. Reeb Ins)tut für Informa)k I12 Short SQL Recap schema typed data tables defined layout space consump)on is computable

More information

hashfs Applying Hashing to Op2mize File Systems for Small File Reads

hashfs Applying Hashing to Op2mize File Systems for Small File Reads hashfs Applying Hashing to Op2mize File Systems for Small File Reads Paul Lensing, Dirk Meister, André Brinkmann Paderborn Center for Parallel Compu2ng University of Paderborn Mo2va2on and Problem Design

More information

Scaling MongoDB: Avoiding Common Pitfalls. Jon Tobin Senior Systems

Scaling MongoDB: Avoiding Common Pitfalls. Jon Tobin Senior Systems Scaling MongoDB: Avoiding Common Pitfalls Jon Tobin Senior Systems Engineer Jon.Tobin@percona.com @jontobs www.linkedin.com/in/jonathanetobin Agenda Document Design Data Management Replica3on & Failover

More information

Scaling the Wholesale Interconnect Market. Gastón Cu0gnola Senior Sales Engineer Telco Systems

Scaling the Wholesale Interconnect Market. Gastón Cu0gnola Senior Sales Engineer Telco Systems Host Sponsor Co- Sponsor Scaling the Wholesale Interconnect Market Gastón Cu0gnola Senior Sales Engineer Telco Systems 1 Presenta0on Agenda Status of Wholesale/Interconnect Environments Moving up the curve

More information

CSCI 599 Class Presenta/on. Zach Levine. Markov Chain Monte Carlo (MCMC) HMM Parameter Es/mates

CSCI 599 Class Presenta/on. Zach Levine. Markov Chain Monte Carlo (MCMC) HMM Parameter Es/mates CSCI 599 Class Presenta/on Zach Levine Markov Chain Monte Carlo (MCMC) HMM Parameter Es/mates April 26 th, 2012 Topics Covered in this Presenta2on A (Brief) Review of HMMs HMM Parameter Learning Expecta2on-

More information

Mul$media Networking. #9 CDN Solu$ons Semester Ganjil 2012 PTIIK Universitas Brawijaya

Mul$media Networking. #9 CDN Solu$ons Semester Ganjil 2012 PTIIK Universitas Brawijaya Mul$media Networking #9 CDN Solu$ons Semester Ganjil 2012 PTIIK Universitas Brawijaya Schedule of Class Mee$ng 1. Introduc$on 2. Applica$ons of MN 3. Requirements of MN 4. Coding and Compression 5. RTP

More information

Transac'onal Libraries Alexander Spiegelman *, Guy Golan-Gueta, and Idit Keidar * Technion Yahoo Research

Transac'onal Libraries Alexander Spiegelman *, Guy Golan-Gueta, and Idit Keidar * Technion Yahoo Research Transac'onal Libraries Alexander Spiegelman *, Guy Golan-Gueta, and Idit Keidar * * Technion Yahoo Research 1 Mul'-Threading is Everywhere 2 Agenda Mo@va@on Concurrent Data Structure Libraries (CDSLs)

More information

Habanero-Java Library: a Java 8 Framework for Multicore Programming

Habanero-Java Library: a Java 8 Framework for Multicore Programming Habanero-Java Library: a Java 8 Framework for Multicore Programming PPPJ 2014 September 25, 2014 Shams Imam, Vivek Sarkar shams@rice.edu, vsarkar@rice.edu Rice University https://wiki.rice.edu/confluence/display/parprog/hj+library

More information

OpenWorld 2015 Oracle Par22oning

OpenWorld 2015 Oracle Par22oning OpenWorld 2015 Oracle Par22oning Did You Think It Couldn t Get Any Be6er? Safe Harbor Statement The following is intended to outline our general product direc2on. It is intended for informa2on purposes

More information

Conges'on. Last Week: Discovery and Rou'ng. Today: Conges'on Control. Distributed Resource Sharing. Conges'on Collapse. Conges'on

Conges'on. Last Week: Discovery and Rou'ng. Today: Conges'on Control. Distributed Resource Sharing. Conges'on Collapse. Conges'on Last Week: Discovery and Rou'ng Provides end-to-end connectivity, but not necessarily good performance Conges'on logical link name Michael Freedman COS 461: Computer Networks Lectures: MW 10-10:50am in

More information

Fine-grained Transaction Scheduling in Replicated Databases via Symbolic Execution

Fine-grained Transaction Scheduling in Replicated Databases via Symbolic Execution Fine-grained Transaction Scheduling in Replicated Databases via Symbolic Execution Raminhas pedro.raminhas@tecnico.ulisboa.pt Stage: 2 nd Year PhD Student Research Area: Dependable and fault-tolerant systems

More information

There is a tempta7on to say it is really used, it must be good

There is a tempta7on to say it is really used, it must be good Notes from reviews Dynamo Evalua7on doesn t cover all design goals (e.g. incremental scalability, heterogeneity) Is it research? Complexity? How general? Dynamo Mo7va7on Normal database not the right fit

More information

Infrastructure Analy=cs: Driving Outcomes through Prac=cal Uses and Applied Data Science at Cisco

Infrastructure Analy=cs: Driving Outcomes through Prac=cal Uses and Applied Data Science at Cisco Copyright 2016 Splunk Inc. Infrastructure Analy=cs: Driving Outcomes through Prac=cal Uses and Applied Data Science at Cisco MaM Birkner Ian Hasund Robert Novak Dis=nguished Engineer, Cisco Chief Architect,

More information

Extending Heuris.c Search

Extending Heuris.c Search Extending Heuris.c Search Talk at Hebrew University, Cri.cal MAS group Roni Stern Department of Informa.on System Engineering, Ben Gurion University, Israel 1 Heuris.c search 2 Outline Combining lookahead

More information

Design Principles & Prac4ces

Design Principles & Prac4ces Design Principles & Prac4ces Robert France Robert B. France 1 Understanding complexity Accidental versus Essen4al complexity Essen%al complexity: Complexity that is inherent in the problem or the solu4on

More information

Op#mizing PGAS overhead in a mul#-locale Chapel implementa#on of CoMD

Op#mizing PGAS overhead in a mul#-locale Chapel implementa#on of CoMD Op#mizing PGAS overhead in a mul#-locale Chapel implementa#on of CoMD Riyaz Haque and David F. Richards This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore

More information

Stay Informed During and AEer OpenWorld

Stay Informed During and AEer OpenWorld Stay Informed During and AEer OpenWorld TwiIer: @OracleBigData, @OracleExadata, @Infrastructure Follow #CloudReady LinkedIn: Oracle IT Infrastructure Oracle Showcase Page Oracle Big Data Oracle Showcase

More information

Advanced branch predic.on algorithms. Ryan Gabrys Ilya Kolykhmatov

Advanced branch predic.on algorithms. Ryan Gabrys Ilya Kolykhmatov Advanced branch predic.on algorithms Ryan Gabrys Ilya Kolykhmatov Context Branches are frequent: 15-25 % A branch predictor allows the processor to specula.vely fetch and execute instruc.ons down the predicted

More information

Combining Real Time Emula0on of Digital Communica0ons between Distributed Embedded Control Nodes with Real Time Power System Simula0on

Combining Real Time Emula0on of Digital Communica0ons between Distributed Embedded Control Nodes with Real Time Power System Simula0on 1 Combining Real Time Emula0on of Digital Communica0ons between Distributed Embedded Control Nodes with Real Time Power System Simula0on Ziyuan Cai and Ming Yu Electrical and Computer Eng., Florida State

More information

MapReduce. Cloud Computing COMP / ECPE 293A

MapReduce. Cloud Computing COMP / ECPE 293A Cloud Computing COMP / ECPE 293A MapReduce Jeffrey Dean and Sanjay Ghemawat, MapReduce: simplified data processing on large clusters, In Proceedings of the 6th conference on Symposium on Opera7ng Systems

More information

@ COUCHBASE CONNECT. Using Couchbase. By: Carleton Miyamoto, Michael Kehoe Version: 1.1w LinkedIn Corpora3on

@ COUCHBASE CONNECT. Using Couchbase. By: Carleton Miyamoto, Michael Kehoe Version: 1.1w LinkedIn Corpora3on @ COUCHBASE CONNECT Using Couchbase By: Carleton Miyamoto, Michael Kehoe Version: 1.1w Overview The LinkedIn Story Enter Couchbase Development and Opera3ons Clusters and Numbers Opera3onal Tooling Carleton

More information

Everything You Need to Know About MySQL Group Replication

Everything You Need to Know About MySQL Group Replication Everything You Need to Know About MySQL Group Replication Luís Soares (luis.soares@oracle.com) Principal Software Engineer, MySQL Replication Lead Copyright 2017, Oracle and/or its affiliates. All rights

More information

ML4Bio Lecture #1: Introduc3on. February 24 th, 2016 Quaid Morris

ML4Bio Lecture #1: Introduc3on. February 24 th, 2016 Quaid Morris ML4Bio Lecture #1: Introduc3on February 24 th, 216 Quaid Morris Course goals Prac3cal introduc3on to ML Having a basic grounding in the terminology and important concepts in ML; to permit self- study,

More information

CS6200 Informa.on Retrieval. David Smith College of Computer and Informa.on Science Northeastern University

CS6200 Informa.on Retrieval. David Smith College of Computer and Informa.on Science Northeastern University CS6200 Informa.on Retrieval David Smith College of Computer and Informa.on Science Northeastern University Indexing Process Indexes Indexes are data structures designed to make search faster Text search

More information

TerraSwarm. A Machine Learning and Op0miza0on Toolkit for the Swarm. Ilge Akkaya, Shuhei Emoto, Edward A. Lee. University of California, Berkeley

TerraSwarm. A Machine Learning and Op0miza0on Toolkit for the Swarm. Ilge Akkaya, Shuhei Emoto, Edward A. Lee. University of California, Berkeley TerraSwarm A Machine Learning and Op0miza0on Toolkit for the Swarm Ilge Akkaya, Shuhei Emoto, Edward A. Lee University of California, Berkeley TerraSwarm Tools Telecon 17 November 2014 Sponsored by the

More information

MegaPipe: A New Programming Interface for Scalable Network I/O

MegaPipe: A New Programming Interface for Scalable Network I/O MegaPipe: A New Programming Interface for Scalable Network I/O Sangjin Han in collabora=on with Sco? Marshall Byung- Gon Chun Sylvia Ratnasamy University of California, Berkeley Yahoo! Research tl;dr?

More information

Crea%ng and U%lizing Linked Open Sta%s%cal Data for the Development of Advanced Analy%cs Services E. Kalampokis, A. Karamanou, A. Nikolov, P.

Crea%ng and U%lizing Linked Open Sta%s%cal Data for the Development of Advanced Analy%cs Services E. Kalampokis, A. Karamanou, A. Nikolov, P. Crea%ng and U%lizing Linked Open Sta%s%cal Data for the Development of Advanced Analy%cs Services E. Kalampokis, A. Karamanou, A. Nikolov, P. Haase, R. Cyganiak, B. Roberts, P. Hermans, E. Tambouris, K.

More information

10. Replication. CSEP 545 Transaction Processing Philip A. Bernstein. Copyright 2003 Philip A. Bernstein. Outline

10. Replication. CSEP 545 Transaction Processing Philip A. Bernstein. Copyright 2003 Philip A. Bernstein. Outline 10. Replication CSEP 545 Transaction Processing Philip A. Bernstein Copyright 2003 Philip A. Bernstein 1 Outline 1. Introduction 2. Primary-Copy Replication 3. Multi-Master Replication 4. Other Approaches

More information

Networks and Opera/ng Systems Chapter 13: Scheduling

Networks and Opera/ng Systems Chapter 13: Scheduling Networks and Opera/ng Systems Chapter 13: Scheduling (252 0062 00) Donald Kossmann & Torsten Hoefler Frühjahrssemester 2013 Systems Group Department of Computer Science ETH Zürich Last /me Process concepts

More information

NFS. CSE/ISE 311: Systems Administra5on

NFS. CSE/ISE 311: Systems Administra5on NFS CSE/ISE 311: Systems Administra5on Sharing files is useful Overview Network file systems give users seamless integra8on of a shared file system with the local file system Many op8ons: NFS, SMB/CIFS,

More information

Database design and implementation CMPSCI 645. Lectures 18: Transactions and Concurrency

Database design and implementation CMPSCI 645. Lectures 18: Transactions and Concurrency Database design and implementation CMPSCI 645 Lectures 18: Transactions and Concurrency 1 DBMS architecture Query Parser Query Rewriter Query Op=mizer Query Executor Lock Manager Concurrency Control Access

More information

1/10/16. RPC and Clocks. Tom Anderson. Last Time. Synchroniza>on RPC. Lab 1 RPC

1/10/16. RPC and Clocks. Tom Anderson. Last Time. Synchroniza>on RPC. Lab 1 RPC RPC and Clocks Tom Anderson Go Synchroniza>on RPC Lab 1 RPC Last Time 1 Topics MapReduce Fault tolerance Discussion RPC At least once At most once Exactly once Lamport Clocks Mo>va>on MapReduce Fault Tolerance

More information

RaceMob: Crowdsourced Data Race Detec,on

RaceMob: Crowdsourced Data Race Detec,on RaceMob: Crowdsourced Data Race Detec,on Baris Kasikci, Cris,an Zamfir, and George Candea School of Computer & Communica3on Sciences Data Races to shared memory loca,on By mul3ple threads At least one

More information

DD2451 Parallel and Distributed Computing --- FDD3008 Distributed Algorithms

DD2451 Parallel and Distributed Computing --- FDD3008 Distributed Algorithms DD2451 Parallel and Distributed Computing --- FDD3008 Distributed Algorithms Lecture 9 Fault Tolerance Mads Dam Autumn/Winter 2011 Much material due to R. Wa2enhofer Overview Introduc9on Strong Consistency

More information

ECE 1749H: Interconnec1on Networks for Parallel Computer Architectures: Rou1ng. Prof. Natalie Enright Jerger

ECE 1749H: Interconnec1on Networks for Parallel Computer Architectures: Rou1ng. Prof. Natalie Enright Jerger ECE 1749H: Interconnec1on Networks for Parallel Computer Architectures: Rou1ng Prof. Natalie Enright Jerger Rou1ng Overview Discussion of topologies assumed ideal rou1ng In prac1ce Rou1ng algorithms are

More information

Today s Objec2ves. Kerberos. Kerberos Peer To Peer Overlay Networks Final Projects

Today s Objec2ves. Kerberos. Kerberos Peer To Peer Overlay Networks Final Projects Today s Objec2ves Kerberos Peer To Peer Overlay Networks Final Projects Nov 27, 2017 Sprenkle - CSCI325 1 Kerberos Trusted third party, runs by default on port 88 Security objects: Ø Ticket: token, verifying

More information

Concurrency-Optimized I/O For Visualizing HPC Simulations: An Approach Using Dedicated I/O Cores

Concurrency-Optimized I/O For Visualizing HPC Simulations: An Approach Using Dedicated I/O Cores Concurrency-Optimized I/O For Visualizing HPC Simulations: An Approach Using Dedicated I/O Cores Ma#hieu Dorier, Franck Cappello, Marc Snir, Bogdan Nicolae, Gabriel Antoniu 4th workshop of the Joint Laboratory

More information

Datacenter replication solution with quasardb

Datacenter replication solution with quasardb Datacenter replication solution with quasardb Technical positioning paper April 2017 Release v1.3 www.quasardb.net Contact: sales@quasardb.net Quasardb A datacenter survival guide quasardb INTRODUCTION

More information

Flash Reliability in Produc4on: The Importance of Measurement and Analysis in Improving System Reliability

Flash Reliability in Produc4on: The Importance of Measurement and Analysis in Improving System Reliability Flash Reliability in Produc4on: The Importance of Measurement and Analysis in Improving System Reliability Bianca Schroeder University of Toronto (Currently on sabbatical at Microsoft Research Redmond)

More information

OLTP on Hadoop: Reviewing the first Hadoop- based TPC- C benchmarks

OLTP on Hadoop: Reviewing the first Hadoop- based TPC- C benchmarks OLTP on Hadoop: Reviewing the first Hadoop- based TPC- C benchmarks Monte Zweben Co- Founder and Chief Execu6ve Officer John Leach Co- Founder and Chief Technology Officer September 30, 2015 The Tradi6onal

More information

Enhancing Throughput of

Enhancing Throughput of Enhancing Throughput of NCA 2017 Zhongmiao Li, Peter Van Roy and Paolo Romano Enhancing Throughput of Partially Replicated State Machines via NCA 2017 Zhongmiao Li, Peter Van Roy and Paolo Romano Enhancing

More information

Assignment 12: Commit Protocols and Replication Solution

Assignment 12: Commit Protocols and Replication Solution Data Modelling and Databases Exercise dates: May 24 / May 25, 2018 Ce Zhang, Gustavo Alonso Last update: June 04, 2018 Spring Semester 2018 Head TA: Ingo Müller Assignment 12: Commit Protocols and Replication

More information

From click to predict and back: ML pipelines at OK. Dmitry Bugaychenko

From click to predict and back: ML pipelines at OK. Dmitry Bugaychenko From click to predict and back: ML pipelines at OK Dmitry Bugaychenko OK is 70 000 000+ monthly unique users OK is 800 000 000+ family links in the social graph OK is A place where people share their posi9ve

More information

Data Modeling and Databases Ch 14: Data Replication. Gustavo Alonso, Ce Zhang Systems Group Department of Computer Science ETH Zürich

Data Modeling and Databases Ch 14: Data Replication. Gustavo Alonso, Ce Zhang Systems Group Department of Computer Science ETH Zürich Data Modeling and Databases Ch 14: Data Replication Gustavo Alonso, Ce Zhang Systems Group Department of Computer Science ETH Zürich Database Replication What is database replication The advantages of

More information

Monitoring IPv6 Content Accessibility and Reachability. Contact: R. Guerin University of Pennsylvania

Monitoring IPv6 Content Accessibility and Reachability. Contact: R. Guerin University of Pennsylvania Monitoring IPv6 Content Accessibility and Reachability Contact: R. Guerin (guerin@ee.upenn.edu) University of Pennsylvania Outline Goals and scope So=ware overview Func@onality, performance, and requirements

More information

Introduction to MySQL InnoDB Cluster

Introduction to MySQL InnoDB Cluster 1 / 148 2 / 148 3 / 148 Introduction to MySQL InnoDB Cluster MySQL High Availability made easy Percona Live Europe - Dublin 2017 Frédéric Descamps - MySQL Community Manager - Oracle 4 / 148 Safe Harbor

More information

What were his cri+cisms? Classical Methodologies:

What were his cri+cisms? Classical Methodologies: 1 2 Classifica+on In this scheme there are several methodologies, such as Process- oriented, Blended, Object Oriented, Rapid development, People oriented and Organisa+onal oriented. According to David

More information

Concurrency Control II and Distributed Transactions

Concurrency Control II and Distributed Transactions Concurrency Control II and Distributed Transactions CS 240: Computing Systems and Concurrency Lecture 18 Marco Canini Credits: Michael Freedman and Kyle Jamieson developed much of the original material.

More information

Overview of IPTV Forum Japan s Hybridcast Technical SpecificaAon

Overview of IPTV Forum Japan s Hybridcast Technical SpecificaAon The fourth Web and TV Workshop Overview of IPTV Forum Japan s Hybridcast Technical SpecificaAon Kinji Matsumura, NHK 1 What is Technology pladorm for broadcast and broadband hybrid service that uses HTML5

More information

Chapter 20: Database System Architectures

Chapter 20: Database System Architectures Chapter 20: Database System Architectures Chapter 20: Database System Architectures Centralized and Client-Server Systems Server System Architectures Parallel Systems Distributed Systems Network Types

More information

Execu&on Templates: Caching Control Plane Decisions for Strong Scaling of Data Analy&cs

Execu&on Templates: Caching Control Plane Decisions for Strong Scaling of Data Analy&cs Execu&on Templates: Caching Control Plane Decisions for Strong Scaling of Data Analy&cs Omid Mashayekhi Hang Qu Chinmayee Shah Philip Levis July 13, 2017 2 Cloud Frameworks SQL Streaming Machine Learning

More information

RouteBricks: Exploi2ng Parallelism to Scale So9ware Routers

RouteBricks: Exploi2ng Parallelism to Scale So9ware Routers RouteBricks: Exploi2ng Parallelism to Scale So9ware Routers Mihai Dobrescu and etc. SOSP 2009 Presented by Shuyi Chen Mo2va2on Router design Performance Extensibility They are compe2ng goals Hardware approach

More information

CISC327 - So*ware Quality Assurance

CISC327 - So*ware Quality Assurance CISC327 - So*ware Quality Assurance Lecture 12 Black Box Tes?ng CISC327-2003 2017 J.R. Cordy, S. Grant, J.S. Bradbury, J. Dunfield Black Box Tes?ng Outline Last?me we con?nued with black box tes?ng and

More information

CISC327 - So*ware Quality Assurance

CISC327 - So*ware Quality Assurance CISC327 - So*ware Quality Assurance Lecture 12 Black Box Tes?ng CISC327-2003 2017 J.R. Cordy, S. Grant, J.S. Bradbury, J. Dunfield Black Box Tes?ng Outline Last?me we con?nued with black box tes?ng and

More information

Informa)on Retrieval and Map- Reduce Implementa)ons. Mohammad Amir Sharif PhD Student Center for Advanced Computer Studies

Informa)on Retrieval and Map- Reduce Implementa)ons. Mohammad Amir Sharif PhD Student Center for Advanced Computer Studies Informa)on Retrieval and Map- Reduce Implementa)ons Mohammad Amir Sharif PhD Student Center for Advanced Computer Studies mas4108@louisiana.edu Map-Reduce: Why? Need to process 100TB datasets On 1 node:

More information