Drobo Performance Stats
Some discussions on twitter last week triggered the topic of performance relating to the Drobo’s. This is the 5th consecutive post on Drobo Series of products.
To read other Drobo related posts:
Drobo S and DroboElite – Introduced 11/23/2009
Some very interesting articles on Drobo S and DroboElite
PLEASE SEE THE ATTACHED PDF FOR PERFORMANCE DATA
Here are some performance stats collected with running Drobo as a direct attached storage and using some benchmarking tools to compile these results. All the performance stats are collected using different criteria’s that can affect the performance of the Drobo. Also used various connection methods including USB and Firewire to obtain these stats.
The entire series of tests have been performed using Mac OSX 10.6.2 host with either USB attached or Firewire attached to the Drobo.
These results are limited to the Drobo and cannot be compared to the Drobo Pro or Drobo Elite or Drobo S.
The test were carried out with using various combination of drives, rebuilt data protection, best-case scenario, worst-case scenario, 1 drive, 2 drives, 4 drives, different drive cache & capacity.
Enjoy!!!
Related posts:
First look performance seems to be limited by internal disk cache size. If they are not disabling it to use DRAM instead that what the performance of this box will be…limited…
That is how high end NAS build appliances. What about SLC or even MLC SSD support rather than just SATA…that will be the ultimate test.
Not sure though the Drobo can even support an SSD because to my understanding it today only supports SATA. The way i look at this is the USB and Firewire interfaces will not exceed beyond certain speeds and since the Drobo is not a NAS device, hard to achieve any more bandwidth beyond the native speed of USB & Firewire….
Though now the e-SATA connection is available on the Drobo S, we may see 30 to 50% better performance on it with that interface, but that would still mean we can only stretch to may be 80 mb/sec IO rates.
SSD are available with SATA interface….
Right! Firewire or USB-2 is the bottleneck too.
Wait for USB-3…then you will forget eSATA and GB Ethernet too.
I forgot. Disk metrics are based on the four following things: Capacity, MB/sec, latency and IOPS. Typically when IOPS is high throughput is low and high throughput is low IOPS. Latecy affect IOPS mainly of course.
Database likes to have low latency along with high IOPS. File serving likes MB/sec and good IOPS too with small file.
It will be nice to see benchmarks similar to what Storage Performance Councils do here with the majors..
http://www.storageperformance.org
Here is a good tool that generate that kind of traffic
http://blogs.sun.com/henk/entry/vdbench_a_disk_...
Let me do some digging on USB 3, hopefully expected to go beyond GigE?
Let me play around with the workload generator tools on the Drobo. Planning for similar benchmarks on other devices as well, stay tuned…
SSD are available with SATA interface….
Right! Firewire or USB-2 is the bottleneck too.
Wait for USB-3…then you will forget eSATA and GB Ethernet too.
I forgot. Disk metrics are based on the four following things: Capacity, MB/sec, latency and IOPS. Typically when IOPS is high throughput is low and high throughput is low IOPS. Latecy affect IOPS mainly of course.
Database likes to have low latency along with high IOPS. File serving likes MB/sec and good IOPS too with small file.
It will be nice to see benchmarks similar to what Storage Performance Councils do here with the majors..
http://www.storageperformance.org
Here is a good tool that generate that kind of traffic
http://blogs.sun.com/henk/entry/vdbench_a_disk_...
Let me do some digging on USB 3, hopefully expected to go beyond GigE?
Let me play around with the workload generator tools on the Drobo. Planning for similar benchmarks on other devices as well, stay tuned…