Attention!
Since this thread is getting longer and longer, not to mention the load times, Christian and I decided to close this thread and start a new one.
The new thread is available here:
[VMware Communities User Moderator|http://communities.vmware.com/docs/DOC-2444][/i]
My idea is to create an open thread with uniform tests whereby the results will be all inofficial and w/o any
warranty.
If anybody shouldn't be agreed with some results then he can make own tests and presents
his/her results too.
I hope this way to classify the different systems and give a "neutral" performance comparison.
Additionally I will mention that the performance is one of many aspects to choose the right system.
The others could be e.g.
\- support quality
\- system management integration
\- distribution
\- self made experiences
\- additional features
\- costs for storage system and infrastructure, etc.
There are examples of IOMETER Tests:
=====================================
\######## TEST NAME: Max Throughput-100%Read
size,% of size,% reads,% random,delay,burst,align,reply
32768,100,100,0,0,1,0,0
\######## TEST NAME: RealLife-60%Rand-65%Read
size,% of size,% reads,% random,delay,burst,align,reply
8192,100,65,60,0,1,0,0
\######## TEST NAME: Max Throughput-50%Read
size,% of size,% reads,% random,delay,burst,align,reply
32768,100,50,0,0,1,0,0
\######## TEST NAME: Random-8k-70%Read
size,% of size,% reads,% random,delay,burst,align,reply
8192,100,70,100,0,1,0,0
The global options are:
=====================================
Worker
Worker 1
Worker type
DISK
Default target settings for worker
Number of outstanding IOs,test connection rate,transactions per connection
64,ENABLED,500
Disk maximum size,starting sector
8000000,0
Run time = 5 min
For testing the disk C is configured and the test file (8000000 sectors) will be created by
first running - you need free space on the disk.
The cache size has direct influence on results. By systems with cache over 2GB the test
file should be increased.
LINK TO IOMETER:
Significant results are: Av. Response time, Av. IOS/sek, Av. MB/s
To mention are: what server (vm or physical), Processor number/type; What storage system, How many disks
Here the config file *.icf
\####################################### BEGIN of *.icf
Version 2004.07.30
'TEST SETUP ====================================================================
'Test Description
IO-Test
'Run Time
' hours minutes seconds
0 5 0
'Ramp Up Time (s)
0
'Default Disk Workers to Spawn
NUMBER_OF_CPUS
'Default Network Workers to Spawn
0
'Record Results
ALL
'Worker Cycling
' start step step type
1 5 LINEAR
'Disk Cycling
' start step step type
1 1 LINEAR
'Queue Depth Cycling
' start end step step type
8 128 2 EXPONENTIAL
'Test Type
NORMAL
'END test setup
'RESULTS DISPLAY ===============================================================
'Update Frequency,Update Type
4,WHOLE_TEST
'Bar chart 1 statistic
Total I/Os per Second
'Bar chart 2 statistic
Total MBs per Second
'Bar chart 3 statistic
Average I/O Response Time (ms)
'Bar chart 4 statistic
Maximum I/O Response Time (ms)
'Bar chart 5 statistic
% CPU Utilization (total)
'Bar chart 6 statistic
Total Error Count
'END results display
'ACCESS SPECIFICATIONS =========================================================
'Access specification name,default assignment
Max Throughput-100%Read,ALL
'size,% of size,% reads,% random,delay,burst,align,reply
32768,100,100,0,0,1,0,0
'Access specification name,default assignment
RealLife-60%Rand-65%Read,ALL
'size,% of size,% reads,% random,delay,burst,align,reply
8192,100,65,60,0,1,0,0
'Access specification name,default assignment
Max Throughput-50%Read,ALL
'size,% of size,% reads,% random,delay,burst,align,reply
32768,100,50,0,0,1,0,0
'Access specification name,default assignment
Random-8k-70%Read,ALL
'size,% of size,% reads,% random,delay,burst,align,reply
8192,100,70,100,0,1,0,0
'END access specifications
'MANAGER LIST ==================================================================
'Manager ID, manager name
1,PB-W2K3-04
'Manager network address
193.27.20.145
'Worker
Worker 1
'Worker type
DISK
'Default target settings for worker
'Number of outstanding IOs,test connection rate,transactions per connection
64,ENABLED,500
'Disk maximum size,starting sector
8000000,0
'End default target settings for worker
'Assigned access specs
'End assigned access specs
'Target assignments
'Target
C:
'Target type
DISK
'End target
'End target assignments
'End worker
'End manager
'END manager list
Version 2004.07.30
\####################################### ENDE of *.icf
TABLE SAMPLE
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
TABLE oF RESULTS
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
SERVER TYPE: VM or PHYS.
CPU TYPE / NUMBER: VCPU / 1
HOST TYPE: Dell PE6850, 16GB RAM; 4x XEON 51xx, 2,66 GHz, DC
STORAGE TYPE / DISK NUMBER / RAID LEVEL: EQL PS3600 x 1 / 14+2 Disks / R50
##################################################################################
TEST NAME--
##################################################################################
Max Throughput-100%Read........__________..........__________.........__________
RealLife-60%Rand-65%Read......__________..........__________.........__________
Max Throughput-50%Read..........__________..........__________.........__________
Random-8k-70%Read.................__________..........__________.........__________
EXCEPTIONS: CPU Util.-XX%;
##################################################################################
I hope YOU JOIN IN !
Regards
Christian
A Google Spreadsheet version is here:
Message was edited by:
ken.cline@hp.com to remove ALL CAPS from thread title
Message was edited by:
RDPetruska
Added link to Atamido's Google Spreadsheet
Well I think this all results here should give more direction for storage choice / throughput - I don't know any other (vendors) virtualisation product that works faster than VMWare and in addition we could saw here (after careful reading the postings) that in fc area the vm's results are only a bit worse that those from ph. servers (iscsi looks a bit more negativ).
And I believe when somebody posts here not truly results there will be always someone correcting them soon.
So I hope VMWare lets this THREAD RUNNING !
AND ONCE AGAIN THE HINT -
remember when your vcpu goes high the cpu clocks cycles (in vm) can change so that the results you can see in iometer are inexactly - one should always verify the results by e.g. VC or storage statistics (the block sizes from the tests are known).
Is there a quick comparison chart with all of this data? It's a bit hard to compare on the different pages and the skewed formatting.
Unfortunately none for now. Sorry.
Maybe Atamido could make one and share?
Sure I could, but then how would I get points for that? 😛
Out of curiousity, where are you getting the "Av. IOs/sek-------Av. MB/sek" in the results? I'm not seeing those listed in the results.csv (using Iometer 2006.07.27). Are you computing them manually from other data?
I have some results I would like to share showing the differences between segment sizes on an IBM DS4300 (FastT 600) dual controller, but want to be sure and post them in the "accepted standard" format.
They all you can see in gui of iometer.
Maybe Atamido could make one and share?
Done.
http://files.commo.de/vmwaresan.html
(Better viewed in Firefox than IE)
A Google Spreadsheet version is here:
http://spreadsheets.google.com/pub?key=p2IFgyUF_v5Jn-7QobgY9Fw
I'd love some help to clean up the spreadsheet and add new entries. If you shoot me your email address, I'll add you as a collaborator.
What I'm seeing is the "Total I/Os per second" and "Total MBs per Second" with no option for "Average" (which I was assuming the Av. stood for). Just to be safe, is the Av. referring to "Total"?
All those values there are average values.
Good job ! Many thanks for that.
Maybe one of forum moderators could put the two links into the first porsting - that would make the search easier! Thanks.
Regards
Christian
I will pm you on friday - today we have here a holiday.
My email-address is:
czimny@kdvz-frechen.de
Regards
Christian
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
TABLE OF RESULTS PHYS. WIN2003 / MS ISCSI INITIATOR / 1 X PS100E
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
SERVER TYPE: Win2003 Std. PHYS.
CPU TYPE / NUMBER: CPU / 2
HOST TYPE: Proliant ML 530 G2, 4GB RAM, 2x XEON 2.4 GHz
STORAGE TYPE / DISK NUMBER / RAID LEVEL: EQL PS100E x 1 / 1x14+2x2 SATA / R50
SAN TYPE / HBAs : iSCSI; iSCSI softw. initiator in WIN2003, 1XGb NIC for iSCSI, Jumbos and Flow Control
##################################################################################
TEST NAME--
##################################################################################
Max Throughput-100%Read........____27____..........___2221___.........___69____
RealLife-60%Rand-65%Read......_____33____..........___1363___.........____11____
Max Throughput-50%Read..........____13____..........___4593___.........____144___
Random-8k-70%Read................._____33____..........___1323___.........____10____
EXCEPTIONS:
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
TABLE OF RESULTS PHYS. WIN2003 / MS ISCSI INITIATOR / 2 X PS100E
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
SERVER TYPE: Win2003 Std. PHYS.
CPU TYPE / NUMBER: CPU / 2
HOST TYPE: Proliant ML 530 G2, 4GB RAM, 2x XEON 2.4 GHz
STORAGE TYPE / DISK NUMBER / RAID LEVEL: EQL PS100E x 2 / 2x14+2x2 SATA / R50
SAN TYPE / HBAs : iSCSI; iSCSI softw. initiator in WIN2003, 1XGb NIC for iSCSI, Jumbos and Flow Control
##################################################################################
TEST NAME--
##################################################################################
Max Throughput-100%Read........____18____..........___3117___.........___97____
RealLife-60%Rand-65%Read......_____22____..........___1939___.........____15____
Max Throughput-50%Read..........____13____..........___4390___.........____137___
Random-8k-70%Read................._____26____..........___1724___.........____14____
EXCEPTIONS:
Ridiz,
thanks for that. First time we can see here 2XPS100 with spanned volumes.
Regards
Christian
Christian, I've been meaning to put those numbers up for a while. This thread has been extremely useful. I'll put up some numbers from ESX later today.
Rich
Ok, remember to verify your vm results e.g. over VC statistics (especially when the vcpu goes high).
Thanks.
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
TABLE OF RESULTS VM on ESX / EqualLogic 1 X PS100E
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
SERVER TYPE: ESX 3.0.1
CPU TYPE / NUMBER: VCPU / 1
HOST TYPE: HP Proliant DL385 G2, 16GB RAM, 2x AMD 2.6 GHz
STORAGE TYPE / DISK NUMBER / RAID LEVEL: EQL PS100E x 1 / 1x14+2x2 SATA / R50
SAN TYPE / HBAs : iSCSI; ESX softw. initiator, 2XGb NIC for iSCSI
##################################################################################
TEST NAME--
##################################################################################
Max Throughput-100%Read........____16____..........___3485___.........__109____
RealLife-60%Rand-65%Read......_____46____..........___874___.........____6.8____
Max Throughput-50%Read..........____5____..........___1338___.........____42___
Random-8k-70%Read................._____57____..........___701___.........____6____
EXCEPTIONS: Done a few months ago w/ 3 hosts and about 30 VMs connected to storage
\##################################################################################
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
TABLE OF RESULTS VM on ESX / EqualLogic 2 X PS100E
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
SERVER TYPE: ESX 3.0.1
CPU TYPE / NUMBER: VCPU / 1
HOST TYPE: HP Proliant DL385 G2, 16GB RAM, 2x AMD 2.6 GHz
STORAGE TYPE / DISK NUMBER / RAID LEVEL: EQL PS100E x 2 / 2x14+2x2 SATA / R50
SAN TYPE / HBAs : iSCSI; ESX softw. initiator, 2XGb NIC for iSCSI
##################################################################################
TEST NAME--
##################################################################################
Max Throughput-100%Read........____17____..........___3416___.........__107____
RealLife-60%Rand-65%Read......_____47____..........___852___.........____6.7____
Max Throughput-50%Read..........____5____..........___1526___.........____48___
Random-8k-70%Read................._____52____..........___770___.........____6____
EXCEPTIONS: These tests were done a couple months apart and the load on the group
has changed. This was run with 6 hosts and about 60 VMs connected to the storage.
\##################################################################################
Christian, I am not clear on what you mean by verify my number vs. VC. If I check VC
during the runs, I get 111, 8, 51 and 8 MB/sek peak respectively. If this isn't
what you meant, please let me know and I will rerun (I can only run the 2xPS100E now).
Thanks,
Rich
Yes VC statistics are mentioned.
When you made your test with ph. server
\- were the 60 vms still running,
\- was your volume spanned over 2 members with config it to R50 (or automatic)
\- to the tests with vms - what I noticed now/(ca. 30 vms running by me) is, that
when I set the volume to be spanned over 2 members I can't reach more ios than by volume to be configured only on one member and the capacity of this volume won't be distributed equal over the 2 members- that seems to be proportional to used space on each member - I missing here the more throughput, by first test I saw definitely much more ios (but there woren't any other vms on storage running then).
Can you see that phenomena too?
Have you tried not to spann the volumes and check the performance?