1. Resource Mapping A Wait Time Based Methodology for Database Performance Analysis Prepared for NoCOUG, Fall Conference, 2004 Presented by Matt Larson Chief Technology Officer Confio Software

2. 2 Presentation Agenda  Introduction  Conventional Tuning vs. Wait-based Tuning  Foundation: Resource Mapping Methodology  5 Key Steps of Applying RMM  RMM Advantages  Conclusion

3. 3 Who am I?  Former DBA consultant specializing in Oracle performance tuning  Co-author of three Oracle books (Oracle Development Unleashed, Oracle Unleashed 2 nd Edition, Oracle8 Server Unleashed)  Co-author of two other database related books  CTO and founder of Oracle performance software company

4. 4 Problems with Conventional Tuning Tools: Like the Drunk Under the Streetlight

5. 5 Conventional Tuning  Art, not a science  Ratio-based (cache hit ratios, etc.)  Sometimes fruitless  It’s “tuned” (I guess?)  Different tuning/investigation process for each DBA/DBA Team/Company

6. 6 Problems with Conventional Tuning Tools  Optimize systems, not business results  Conventional tools: V$ Views: limited visibility & granularity Statspack: averages across entire database Tracing: Limited to session, excessive volume  Incorrect Data hides real results System-wide averages Event counters Incomplete visibility

7. 7 What Problems are you Trying to Solve?  Methodology addresses a common problem space: I spend the whole week monitoring and optimizing Oracle configurations, but I have no demonstrable results to show for it - why? Will more hardware make my application run faster? By how much? Will the new application run efficiently on the production server? Why does one application keep impacting my SLA compliance? If I could make one (or 2, 3, or 4) changes to my database to have the biggest impact, what would they be?

8. 8 You know you are working on the wrong thing when…  After spending an agonizing week tuning Oracle buffers to minimize I/O operations, management typically rewards you with: A. An all expense paid vacation B. A free lunch C. A stale donut D. Reward? Nobody even noticed!

9. 9 You know you have a visibility problem when…  You measure database performance based on: A. Increasing trends in user response time B. Increasing system down time C. Increasing help desk calls D. Increasing decibel levels from irate users

10. 10 Your role is sub-essential to the business of your organization when…  Your role in the rollout of a new customer facing application results in: A. Keys to drive the CEO’s Porsche B. Keys to use the executive restroom C. A mop to use in the executive restroom D. Your office has been moved to the restroom

11. 11 You know you are accustomed to measuring the wrong thing when…  You measure the commute time to work based on: A. The time it takes to get there B. Counting the times your wheels rotate C. Monitoring your tachometer D. The number of speeding tickets

12. 12 Wait-based Performance Tuning  Emerging best-practice for database tuning  Proponents include leading consultants, trainers and authors  Oracle is starting to build wait-based tuning tools into the database particularly in 10g  Tune by determining where processing time is spent

13. 13 Oracle 10g - Moving towards wait-based  Adding wait-based columns to existing views  New wait-based views Example: v$session_wait_history Provides the last 10 wait events for a session Session ID, Username, Event, Wait_Time, etc. Used to provide wait_time for only a few events

14. 14 RMM Resource Mapping Methodology A set of requirements that define what data must be captured to effectively make tuning decisions and a process for applying the data to achieve the optimal outcome Wait Based Tuning

15. 15 DBA Success Stories using RMM  DBA solves a “Cold Case”. Problem unresolved for 1 year with traditional tools; Solution identified in 10 minutes during hands-on training  DBA ends “Crit Sit” 2 week situation ends quickly after identification of Library Cache pin wait and load locks. Metalink identifies Oracle bug, patch successfully applied  DBA saves $700K. 90% CPU capacity initiates expansion from 12 to 24 CPU server. DBA identifies parallel queries across 16 parallel threads as source of bottleneck. CPU eliminated as constraint, no new server required.

16. 16 Resource Mapping Methodology  Three Key Principles of RMM 1. SQL View: View all statistics at SQL statement level 2. Time View: Measure Time, not number of times a resource is utilized 3. Full View: Separately measure every resource to isolate source of problems

17. 17 Illustrating example: SQL View Principle  Example: ‘CEO’ measuring ‘employee’ output  Averaging over entire company gives no useful data  Must measure each job separately  DBA must manage database similarly  Measure and identify bottlenecks for each SQL independently

18. 18 Illustrating example: Time View Principle  Example: ‘CEO’ counting ‘tasks’ vs. ‘time to complete’  Counting system statistics not meaningful  Must measure Time to complete  System stats (buffer size, hit ratios, I/O counts) do not identify where database customers are waiting  Identify and optimize Wait Time for each SQL as best indicator of performance

19. 19 Illustrating example: Full View Principle  Example: ‘CEO’ measuring results with blind spot hiding key processes  Without direct visibility, valuable info is lost  Must have visibility to every process step  Distinctly identify and measure each Oracle resource for each distinct SQL

20. 20 Track SQL Time, Not System Counters SQL 1 SQL 2 SQL 3 ResourcesI/ONetworkRedoLocks Watching Counters leads to wrong conclusions: Time is more relevant Total System Counters hide information: Need breakdown to individual SQLs 5 R 25 R 50 Reads Total System Counter 80K Reads 30 Minutes 15M 5M 6 M 10 M 100 Minutes 35 A 50 A 125 Attempts 4 M 200 Minutes 5M 4 M 200 Minutes 5M 5K Packets216K Writes

21. 21 Applying RMM for Business Results Five Step Process focusing on what matters 1. Identify2. Allocate3. Quantify4. Prioritize5. Assign

22. 22 Step 1: Identify  Identify SQL Statements having largest impact (SQL View and Time View principles)  Longest wait times = most significant “pain points” for customers  Conversely, low cache hit ratios or high latch usage may not impose high wait times for users (so why fix them?) SQL statements prioritized by Total Wait Time

23. 23 Step 2: Allocate  Allocate impact to real customers (internal or external)  Allocate wait time to Program, Session, Machine SQL View principle makes this connection  Understanding database customer and application Programs Prioritized by Total Wait Time

24. 24 Step 3: Quantify  How much is save in time/money if fixed?  Enabled by Full View and Time View principles  Soft dollar savings Data entry clerks DBA time spent in problem resolution  Hard dollar savings Reduce hardware upgrades Meet SLA’s avoiding penality Ensure business isn’t lost due to poor performing or unavailable system Quantifiable benefit of Tuning a specific statement

25. 25 Step 4: Prioritize  If last step properly executed, this step is fairly straight forward  Allow’s DBA to cut through the clutter of potential new projects, investigations, and trials.  Better justification for priorities. (e.g. We aren’t working on your problem since this other has a higher demonstrable business impact)

26. 26 Step 5: Assign  Assign the right people to the problem Log_buffer waits Network issues Same query 10,000/hour  Enabled by Full View principle  Avoid finger-pointing by accurately assigning quickly

27. 27 Resource Mapping Methodology RMM Wait Based Tuning Network, Storage, Application, Web, etc.

28. 28 Web Server Custom Biz Logic Network Database Server Storage Box Software Layers Silo Monitoring Each team uses their own tool to partially monitor their non-Oracle layers. No view across layers. Management has no clear view. Web Team Custom App Team Network Team Database/OS Teams Storage/OS Teams IT Management Business Management Sitescope Often No Commercial Tools HP Openview Wait-based tuning EMC Control Center LIMITED VIEW

29. 29 The Solution - Integrated Vision Web Server Custom Biz Logic Network Database Server Storage Box Web Team Custom App Team Network Team Database/OS Teams Storage/OS Teams All teams see a complete picture of all layers and dependencies. Enables more efficient “Umbrella” solution. RMM across the stack IT Management Business Management

30. 30 RMM Achieved Business Benefits RMM Does:Business Benefit: 35% reduction in database capacity requirement Reduce capital investment Avoid unnecessary additions Recovers un-used capacity Standardizes “expert” analysis ability across entire DBA team Reduce training & consulting costs Quantifies performance impactFocus tuning efforts on biggest business impacts Identifies problem Root Cause and resolution Assign human resources and responsibility Anticipates + resolves performance bottlenecks Maintain SLA and end user performance

31. 31 Example 1: Problem Observed  Critical situation: Secure Service Center application performance unsatisfactory Response time between 2400 and 9000 seconds Very high network traffic (3x—4x normal), indicating time-outs and user refreshes “CritSit” declared: major effort to resolve problem

32. 32 Observations using Resource Mapping Methods Lib cache pin wait Lib cache load lock Notice scale: > 8000 secs  1: Identify accumulated Waits  2: Identify specific resources used

33. 33 Results Library cache pin nearly unobservable Library cache load lock no longer observable Notice scale: < 1400 secs max

34. 34 Results  Response time improvement from 8000 seconds (worst case) to 900 seconds  Variance improvement: Before: response time 2400 - 8000 sec After: response time 800 - 900 sec

35. 35 Example 2: Performance Drain – Identify the Source  Slow response reported  DBA and database focus of delays  Database problem?  No – SQL*Net Message identified as source of delay  2 nd highest wait event

36. 36 RMM Drill Down identifies source of problem  Single application generates all SQL*Net Messages  App on same server as Oracle!  Answer:  Misconfiguration – TCP/IP used within server  Change to IPC, eliminate NIC traffic and 30% of wait time Solution requires knowing: Which SQL, What Wait Time, Which Resource

37. 37 Example 3: Scattered Reads  Situation: LINS06 database - Hourly profile identifies high wait anomaly  3-10x higher than other periods – requires investigation wait time 42,000 seconds 10:00-11:00

38. 38 Drill Down to Key RMM Parameters Db file scattered reads Notice scale: > 6000 secs

39. 39 Conclusion  Look for what has an impact  Resource Mapping is more that Wait Time – Analysis must include: SQL level granularity Full Resource granularity  Isolating the SQL and Resource allows you to find and fix the Root Cause  DBAs can have an impact and be heroes!

40. 40 Thank you for coming Matt Larson Contact Information mattlarson@confio.com 303-938-8282 ext. 110 Company website www.confio.com