MegaRAID Performance Tuning & Benchmark Tips

pages

English

Documents

Lire

Le téléchargement nécessite un accès à la bibliothèque YouScribe Tout savoir sur nos offres

pages

English

Documents

Lire

Le téléchargement nécessite un accès à la bibliothèque YouScribe Tout savoir sur nos offres

Publié par

Inya

Nombre de lectures

5 913

Langue

English

Poids de l'ouvrage

1 Mo

MegaRAID Benchmark Tips
January
27, 2010Benchmark Review Requirements
•
Providing
the following information will improve our ability to support product
evaluations
–
Summary of test cases
you
will
be
performing
–
System details and benchmark
parameters listed
on
slide
3
•
Questions regarding configuration and
benchmark results
should be
addressed to:
–
L
SI Technical
Support
•
support@lsi.com
–
(
For Product Evaluations)
–
C
raig McCombs
•
craig.mccombs@lsi.com
–
J
ames Evans
•
james.evans@lsi.com
LSI Proprietary
2Elements that Effect Performance
•
System
–
M
otherboard,
Chip
Set, BIOS, Processor,
Memory
•
S
ystem chip set and memory s
peed can impact benchmark performance
•
R
ecommend
8-wide (x8) PCIe
Generation-2

slot for all 6 Gb/s SAS
benchmarks
–
O
perating System with latest
Service
Pack and Updates
•
RAID controller
–
Firmware, BIOS,
driver version
–
D
isk
write cache policy
setting
–R
A
I
D
l
e
v
e
l
–
Stripe size
–
R
ead and
Write
Caching policies
•
Drives
–
T
otal
number of drives
•
N
umber of
drives per channel
–
Enclosure model
+
firmware
–
D
rive interface
(SATA, SAS) and
Speed (i.e.
1.5Gb/s,
3Gb/s,
6Gb/s)
–
M
ake and model of drive
–
Firmware version
–
C
lass of
the
drive
(e.g.,
HDD disk
drive,
SSD solid
state,
etc.)
•
Benchmark Tool
–
Test profile ( Block
Size, Sequential
R
ead or Write,
Random Read or Write)
LSI Proprietary
3

Tips
Use the latest firmware for testing the RAID ...

Voir

Publié par

Inya

Nombre de lectures

5 913

Langue

English

Poids de l'ouvrage

1 Mo

MegaRAID Benchmark TipsJanuary 27, 2010

Benchmark Review RequirementsProviding the following information will improve our ability to support product evaluationsSummary of test cases you will be performingSystem details and benchmark parameters listed on slide 3Questions regarding configuration and benchmark results should be addressed to:LSI Technical Supportsupport@lsi.com(For Product Evaluations)Craig McCombscraig.mccombs@lsi.comJames Evansjames.evans@lsi.comLSI Proprietary2

Elements that Effect PerformanceSystemMotherboard, Chip Set, BIOS, Processor, MemorySystem chip set and memory speed can impact benchmark performanceRecommend 8-wide (x8) PCIeGeneration-2 slot for all 6 Gb/s SAS benchmarksOperating System with latest Service Pack and UpdatesRAID controllerFirmware, BIOS, driver versionDisk write cache policy settingRAID levelStripe sizeRead and Write Caching policiesDrivesTotal number of drivesNumber of drives per channel Enclosure model + firmwareDrive interface (SATA, SAS) and Speed (i.e. 1.5Gb/s, 3Gb/s, 6Gb/s)Make and model of driveFirmware versionClass of the drive (e.g., HDD disk drive, SSD solid state, etc.)Benchmark ToolTest profile ( Block Size, Sequential Read or Write, Random Read or Write)LSI Proprietary3

spiTUse the latest firmware for testing the RAID controllerHow to update (flash) RAID on controller FW?MegaRAID Storage Management (MSM)MegaRAID Command Line Interface (MegaCLI)Reboot systemDownload latest FW from MegaRAID DownloadsTo configure the RAID Adapter and create logical arrays use eitherCTRL-H utility during BIOS POSTUse MegaRAID Storage Management (MSM) running from OSUse the latest OS drivers (use Storportdriver when possible)Can be downloaded from MegaRAID DownloadsTo achieve maximum sustained RAID controller throughputFor maximum bandwidth (MB/s) use 64KB to 1MB sequential access patternsFor maximum operations (IO/s) use 0.5KB to 8KB random access pattersConnect enough drives to saturate the RAID controller to achieve maximum performance. For example use 20 or more 15K SAS drives to achieve maximum bandwidth performanceUse all SAS channels connected to drives or drive enclosuresWith multiple drive enclosures make sure drives evenly distributed across enclosuresDrive technology and cache size can significantly impact performanceBenchmark IO request queue depth will impact performance. Recommend IO request queue depth of 16 or greaterLSI Proprietary4

NOStandard Benchmark ToolIOmeteris a I/O performance analysis tool for servers and workstationsObtain latest IOmeterfrom Source ForgeIOmeterUsers Guide IOmeter.orgWindows 32-bit version (2006.07.27) satisfactory for 32-bit or 64-bit OSThroughput is measured in IO/sec and MB/secI/Os per second for random/transactional workloadsMegabytes per second for streaming/sequential workloads(See Appendix for IOmeterworkload configuration examples)TE: LSI canp rovideI OmeterLSI Proprietaryperformancet ests criptst og enerater esults5

yrateirporP ISL.ecnamroMegaRAID Settings for Maximum HDD PerformancefRSAtIriDp e0 ,S i1z e:& 10RWeriated PPoolliiccyy:: rIO Policy: Disk Cache Policy:RAID 5 & 6Stripe Size: Read Policy: Write Policy: IO Policy: Disk Cache Policy:Init State:eBK652Always Read AheadWrite Thru (For streaming sequential performance)Write Back (For transactional/random tests)Direct IOEnabled (1)p6 rehgih ecudorp semitemos nac tnemtsujda retemarap gnihcac lanoitidda ,daolkrow dna noitarugifnoc cificeps a roF .sdaolkrow dna snoitarugifnoc nommoc ssorca stluser lamitpo ecudorp snoitadnemmocer evoba eht eton esaelP)2(ecnamrofrep detimil evird fo secnatsni gniziminiM .sesoprup gnitset rof ecnamrofrep evird secnahnE)1()emulov eritne ssorca atad etirw ro( noitazilaitini lluF)1( delbanEOI tceriDkcaB etirWdaehA daeR syawlABK652

arap gnihcac lanoitidda ,daolkrow dna noitarugifnoc cificeps a roF .sdaolkrow dna snoitarugifnoc nommoc ssorca stluser lamitpo ecudorp snoitadnemmocer evoba eht eton esaelP)3(sDSS rof noitacilppa lacipyt si hcihw ecnamrofrep modnar/lanoitcasnart rof ezimitpO)2(ecnamrofrep detimil evird fo secnatsni gniziminiM .sesoprup gnitset rof ecnamrofrep evird secnahnE)1()emulov eritne ssorca atad etirw ro( noitazilaitini lluF)1( delbanEOI tceriD)2(kcaB etirW)2(daehA daeR oNBK652MegaRAID Settings for Maximum SSD PerformanceRAID 0, 1 & 10Stripe Size: Read Policy: Write Policy: IO Policy: Disk Cache Policy:RAID 5 & 6Stripe Size: Read Policy: Write Policy: IO Policy: Disk Cache Policy:Init State:BK652No Read Ahead(2)Write Thru(2)Direct IOEnabled (1)7yrateirporP ISL.ecnamrofrep rehgih ecudorp semitemos nac tnemtsujda retem

Read PoliciesAdaptive Read AheadThis specifies that the controller uses read-ahead if the two most recent disk accesses occurred in sequential sectors. If all read requests are random, the algorithm reverts to No Read Ahead, however all requests are still evaluated for possible sequential operation.Recommended for all HDD configurationsAlways Read AheadThe controller reads ahead all the data until the end of the stripe from the diskNo Read Ahead Only the requested data is read and the controller does not read ahead any dataRecommended for all SDD configurationsLSI Proprietary8

Caching PoliciesDirect IOAll read data is transferred directly to host memory bypassing RAID controller cache. Any Read Ahead data is cached.All write data is transferred directly from host memory bypassing RAID controller cache if Write-Through cache mode is setRecommended for all configurationsCached IOAll read and write data passes through controller cache memory on its way to or from host memory. Includes write data in Write-Through .edomThis legacy option is being eliminated in a future releaseLSI Proprietary9

Write PoliciesWrite-ThroughCaching strategy where data is written to disks before a completion status is returned to the host operating system Considered more secure, since a power failure will be less likely to cause undetected drive write data loss with no battery-backed cache presentRecommend Write-Through for RAID 0, 1 and 10 and all SSD configurationsProvides optimum performance for streaming/sequential benchmarksiSnitnoc cea dcahtea iwsh imcho vceadn diimrepcrtolyv efr oovme rthalel pheorsfto trom tahnec dei fsokrs ,s titr eaavmoiidnsg cwooprykilnoga tdhs ei f dDaitrae icnt tIeOr mmeodidaer iys .tesWrite-BackA caching strategy where write operations result in a completion status being sent to the host operating system as soon as data is in written to the RAID cache. Data is written to the disk when it is forced out of controller cache memory.Write-Back is more efficient if the temporal and/or spatial locality of the requests is smaller than the controller cache size. Write-Back is more efficient in environments with bursty write activity.Battery backed cache can be used to protect against data loss as a result of a power failure or system crash.Recommend Write-Back for RAID 0, 1, and 10 configurationsProvides optimum performance for transactional(random real world) benchmarksRecommend Write-Back for RAID 5 and 6 configurationsProvides best overall performanceImproves performance of RAID-5 and 6 data redundancy generationLSI Proprietary01

Cache VariablesRAID Controller CacheVarious cache sizes supported on RAID adaptersFaster cache speed improves sequential RAID 5/6 write performance:Example: DDR vsDDRIIExample: 533 MHz vs. 667 MHz vs. 800 MHzMemory bit width will affect RAID 5/6 Seq. write performance72-bit has up to an 18% advantage over 40-bitRecommend high speed and large size RAID cache memorySystem CachePerformance impacted by system chip set and memory speed for many IO workloads. However run IOmeterbenchmark on unformatted (raw) device. This bypasses system cache for accurate storage performance measurements.Drive CacheRecall performance impacted by drive cache size for many IO workloadsLSI Proprietary11

Voir