VMDK : Thin vs thick disks : is there a performance difference?

modern versions of the hypervisor show almost no performance difference between thick and thin for 99% of workloads. -mcowger
Pasted from <http://communities.vmware.com/message/2100863#2100863>




Question : How different is the performance between thick and thin?
So I was thinking most cases thin is as good as thick, but thick is for that extra performance bump.
But things change a lot so I was looking for some hard data to back it up








*This test from planet zorg benchmarks thin vs thick lazy vs thick eager
Comparing the latency and iops they are very similar


1.     I/O of a Thick Provision Lazy Zeroed disk

Test name	Latency	Avg iops	Avg MBps	cpu load
Max Throughput-100%Read	0.00	3491	109	3%
RealLife-60%Rand-65%Read	12.87	4490	25	11%
Max Throughput-50%Read	101.44	6190	193	15%
Random-8k-70%Read	13.96	5681	44	17%

2. I/O of a Thick Provision Eager Zeroed disk

Test name	Latency	Avg iops	Avg MBps	cpu load
Max Throughput-100%Read	0.00	3511	109	1%
RealLife-60%Rand-65%Read	12.78	4460	34	30%
Max Throughput-50%Read	102.88	6261	195	2%
Random-8k-70%Read	14.19	5770	45	34%

3. I/O of a Thin Provision disk

Test name	Latency	Avg iops	Avg MBps	cpu load
Max Throughput-100%Read	0.00	3530	110	0%
RealLife-60%Rand-65%Read	13.06	4566	35	30%
Max Throughput-50%Read	102.36	6243	195	2%
Random-8k-70%Read	14.17	5767	45	36%



Pasted from <http://planetzorg.wordpress.com/2011/08/25/vmware-5-0-disk-io-performance-thick-provision-lazy-zeroed-vs-thick-provision-eager-zeroed-vs-thin-provision/>






White paper from Vmware
This is referenced a lot on the web
Essentially the performance of thin disks is on par with the tick disks
http://www.vmware.com/pdf/vsp_4_thinprov_perf.pdf




Conclusion:
Using data from the web, It seems that thin is just as good as thick in possibly all but the most exteme cases.
Ill run my own tests in the future just to have data, but the evidence points to always using thin disk unless recommended by vmware (or your application vendor).