case study sap hana - warp mechanicswarpmech.com/wp-content/uploads/2014/04/usecase-hana.pdf ·...

2
Case Study SAP HANA Accelerating business with In-Memory transactions Businesses must make smart decisions to stay ahead of the competition. One wrong decision can set a company back months. To reduce risk, businesses have turned to data analytics to examine the variables of their products, customers, partners, and even regulatory and environmental influences to make informed decisions. But the glut of data is overwhelming and the rate of change is beyond the ability of legacy processing systems to keep up. Delayed analysis makes getting current information nearly impossible: there’s so much to gather and analyze that results can be outdated before they come in. Increasing volumes of data plus growing numbers of data sources combine with ordinary processing methods to result in high information latency. That means: Poor Visibility: planning based on outdated info Low Agility: suboptimal execution of business plans Missed Opportunities: “delayed reaction” business model WARP Mechanics and SAP, providers of business intelligence platforms, have developed an advanced system for business analytics that reduces the overhead of transaction processing to deliver actionable information to decision makers. SAP HANA, the high performance analytic appliance, processes massive amounts of real time data in memory to provide immediate results from analysis, regardless of what data sources are involved. This system uses data compression and partitioning with realtime capture, insert on delta, and replication, to streamline dataflows. The WARP MemoryMatrix appliances provide the lowlatency persistent memory storage for unprecedented performance and scalability not found in legacy storage systems, at a price point other solidstate providers can’t match. Inmemory computing, plus datasource independence, plus gigabytes of high IOPS throughput overcomes the delays of legacy analytics engines. This provides: Realtime Information: current information for the best planning Agile Performance: simulate decisions on the fly based on actual data Competitive Advantage: optimized focus and effective spending Performance The HANA InMemory Computing Engine software bundled with WARP Mechanics hardware includes tools for data modeling and life cycle management, security, and operations, and supports multiple interfaces to extract value from any data source and send to any data consumer. Inmemory computing executes all transactions, transformations, and complex data processing. All applications (ERP and BW) run on data residing inmemory and operations work on data in real time. But to accomplish realtime reliable operations, the system requires persistent storage as well as RAM. The HANA persistency layer leverages the power of the WARP MemoryMatrix appliance: a scalable allSSD system that can deliver over 1M IOPS and over 100Gbps of network throughput per 4u shelf. Business Intelligence Challenge Overcome information latency resulting from increased volumes of data, the variety and types of data sources, and delays in calculation speed to process massive amounts of real time data, and provide immediate results from analysis and/or synchronous transactions. Solution WARP Mechanics “MemoryMatrix” storage appliances combined with the power of SAP HANA bring the perfect mix of performance and scalability to business intelligence. RDMA access to pure SSD arrays allows the WARP platform to provide superior throughput and latency, while offloading the CPUs of attached systems. WARP appliances allow greater density for SAP HANA environments because they are built on WARP’s super computing class platforms. Results An SAP HANA cluster running on WARP Mechanics processes massive quantities of real time data at memory speeds, with an affordable price. This results in effective CapEx spending, while supporting business intelligence simulation of multiple variables in real time.

Upload: others

Post on 27-Jun-2020

1 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Case Study SAP HANA - WARP Mechanicswarpmech.com/wp-content/uploads/2014/04/UseCase-HANA.pdf · Case Study SAP HANA Accelerating business with In-Memory transactions Businesses!must!make!smart!decisions!tostay!aheadof!the!competition.!One!wrong!

           

Case Study SAP HANA Accelerating business with In-Memory transactions

Businesses  must  make  smart  decisions  to  stay  ahead  of  the  competition.  One  wrong  decision  can  set  a  company  back  months.  To  reduce  risk,  businesses  have  turned  to  data  analytics  to  examine  the  variables  of  their  products,  customers,  partners,  and  even  regulatory  and  environmental  influences  to  make  informed  decisions.  But  the  glut  of  data  is  overwhelming  and  the  rate  of  change  is  beyond  the  ability  of  legacy  processing  systems  to  keep  up.  Delayed  analysis  makes  getting  current  information  nearly  impossible:  there’s  so  much  to  gather  and  analyze  that  results  can  be  outdated  before  they  come  in.    

Increasing  volumes  of  data  plus  growing  numbers  of  data  sources  combine  with  ordinary  processing  methods  to  result  in  high  information  latency.  That  means:  

• Poor  Visibility:  planning  based  on  outdated  info  

• Low  Agility:  sub-­‐optimal  execution  of  business  plans  

• Missed  Opportunities:  “delayed  reaction”  business  model    

WARP  Mechanics  and  SAP,  providers  of  business  intelligence  platforms,  have  developed  an  advanced  system  for  business  analytics  that  reduces  the  overhead  of  transaction  processing  to  deliver  actionable  information  to  decision  makers.  SAP  HANA,  the  high-­‐performance  analytic  appliance,  processes  massive  amounts  of  real  time  data  in  memory  to  provide  immediate  results  from  analysis,  regardless  of  what  data  sources  are  involved.  This  system  uses  data  compression  and  partitioning  with  real-­‐time  capture,  insert  on  delta,  and  replication,  to  streamline  dataflows.  The  WARP  MemoryMatrix  appliances  provide  the  low-­‐latency  persistent  memory  storage  for  unprecedented  performance  and  scalability  not  found  in  legacy  storage  systems,  at  a  price  point  other  solid-­‐state  providers  can’t  match.  

In-­‐memory  computing,  plus  data-­‐source  independence,  plus  gigabytes  of  high  IOPS  throughput  overcomes  the  delays  of  legacy  analytics  engines.  This  provides:  

• Real-­‐time  Information:  current  information  for  the  best  planning  

• Agile  Performance:  simulate  decisions  on  the  fly  based  on  actual  data  

• Competitive  Advantage:  optimized  focus  and  effective  spending  

Performance The  HANA  In-­‐Memory  Computing  Engine  software  bundled  with  WARP  Mechanics  hardware  includes  tools  for  data  modeling  and  life  cycle  management,  security,  and  operations,  and  supports  multiple  interfaces  to  extract  value  from  any  data  source  and  send  to  any  data  consumer.  In-­‐memory  computing  executes  all  transactions,  transformations,  and  complex  data  processing.  All  applications  (ERP  and  BW)  run  on  data  residing  in-­‐memory  and  operations  work  on  data  in  real  time.  

But  to  accomplish  real-­‐time  reliable  operations,  the  system  requires  persistent  storage  as  well  as  RAM.  The  HANA  persistency  layer  leverages  the  power  of  the  WARP  MemoryMatrix  appliance:  a  scalable  all-­‐SSD  system  that  can  deliver  over  1M  IOPS  and  over  100Gbps  of  network  throughput  per  4u  shelf.

Business Intelligence Challenge

Overcome  information  latency  resulting  from  increased  volumes  of  data,  the  variety  and  types  of  data  sources,  and  delays  in  calculation  speed  to  process  massive  amounts  of  real  time  data,  and  provide  immediate  results  from  analysis  and/or  synchronous  transactions.  

Solution

WARP  Mechanics  “MemoryMatrix”  storage  appliances  combined  with  the  power  of  SAP  HANA  bring  the  perfect  mix  of  performance  and  scalability  to  business  intelligence.  

RDMA  access  to  pure  SSD  arrays  allows  the  WARP  platform  to  provide  superior  throughput  and  latency,  while  offloading  the  CPUs  of  attached  systems.  WARP  appliances  allow  greater  density  for  SAP  HANA  environments  because  they  are  built  on  WARP’s  super  computing  class  platforms.  

Results

An  SAP  HANA  cluster  running  on  WARP  Mechanics  processes  massive  quantities  of  real  time  data  at  memory  speeds,  with  an  affordable  price.  This  results  in  effective  CapEx  spending,  while  supporting  business  intelligence  simulation  of  multiple  variables  in  real  time.  

 

Page 2: Case Study SAP HANA - WARP Mechanicswarpmech.com/wp-content/uploads/2014/04/UseCase-HANA.pdf · Case Study SAP HANA Accelerating business with In-Memory transactions Businesses!must!make!smart!decisions!tostay!aheadof!the!competition.!One!wrong!

 

     

www.WARPmech.com

 

1288 Columbus Ave #176 San Francisco, CA 94133 888-WARP-MECH (+1.888.927.7632) [email protected]

Copyright © 2013 WARP Mechanics Ltd. All Rights Reserved

SAP HANA: Accelerating business with In-Memory transactions

The  platform  has  two  controllers,  each  with  high-­‐speed  processor  and  DRAM.  The  all-­‐SSD  system  removes  the  need  for  a  separate  read  cache  for  active  files,  leaving  more  RAM  for  advanced  features  such  as  clustering,  replication,  de-­‐duplication,  thin  provisioning,  and  snapshots.  

SSD  modules  achieve  maximum  write  and  read  performance  while  still  supporting  high  capacity.  Each  flash  module  can  sustain  ~500MBps,  for  high  throughput  designs  with  <3ms  response  time  latency.  Each  2TB  SSD  exceeds  100,000  read  and  write  IOPS  per  module,  making  the  MemoryMatrix  easily  capable  of  >1  Million  IOPS  per  shelf.  

This  extreme  performance  removes  constraints  on  analyzing  large  data  sets.  The  system  is  ideal  for  data  mining  and  predictive  analytics,  from  both  structured  and  unstructured  data  sources.  

Scale Since  data  can  come  from  any  source,  SAP  HANA  needs  a  storage  subsystem  that  can  grow  and  flex  as  business  needs  change.  A  single  MemoryMatrix  can  start  as  small  as  20TB  and  grow  to  120TB  in  a  single  shelf.    

Legacy  HDD-­‐based  storage  solutions  cannot  match  this  performance  density.  Even  few  pure  memory  vendors  can  approach  either  the  performance  or  capacity  density,  and  none  can  approach  the  price:performance  ratio.  If  business  needs  require  additional  storage,  legacy  OEMs  will  gladly  wheel  in  another  rack  full  of  hardware.  In  contrast,  the  WARP  system  can  scale  to  a  petabyte  of  low-­‐latency  SSD  per  rack,  without  downtime  or  performance  loss.  

Integrity Fast  response  is  nice.  But  fast  and  correct  answers  are  much  more  useful.  History  demonstrates  that  even  a  single-­‐digit  miscalculation  can  bring  down  rockets,  buildings,  and  bridges.  Even  if  the  data  is  committed  to  disk  reliably,  there  is  no  guarantee  it  will  stay  that  way:  many  failure  cases  corrupt  data  within  legacy  RAID  systems,  including  write  holes,  silent  data  corruption,  bit  rot,  and  simultaneous  disk  failures.  

Contemporary  drive  capacities  have  increased  the  occurrence  of  random  bit-­‐flipping  in  storage  subsystems  to  frequent  levels.  Unlike  other  Business  Intelligence  systems  backed  by  legacy  OEM  storage  that  only  provide  traditional  RAID  parity,  WARP  provides  advanced  integrity  features  that  protect  data  from  

corruption.  It  uses  RAID  with  single-­‐,  double-­‐,  or  triple-­‐parity,  and  then  goes  a  step  further.  At  every  phase  of  its  lifecycle,  data  is  protected  by  ECC  memory,  network  checksums  in  flight,  block-­‐level  checksums  at  rest,  unlimited  snapshots  and  clones,  and  real-­‐time  replication.  If  a  bit  flip  occurs  for  any  reason,  it  will  be  detected  and  corrected  through  background  integrity  checks,  ensuring  accurate  data  analysis  and  simulation  both  today  and  in  the  future.  

Conclusion The  MemoryMatrix  family  of  appliances  delivers  throughput  and  scalability  far  beyond  legacy  OEM  products  for  superior  in-­‐memory  analytics  with  SAP  HANA.  Leveraging  enterprise  hardware  and  software,  they  supply  the  highest  levels  of  throughput,  scale,  and  data  protection  at  a  fraction  of  the  cost.  The  power  and  performance  of  a  pure  memory  appliance  provides  real-­‐time  access  to  process  massive  quantities  of  data  at  memory  speeds  –  regardless  of  data  source  –  resulting  in  quite  simply  the  best  preforming  analytics  system  on  the  market  today.