New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
Benchmarks with dd and ioping.
Hi,
We see lot's of of benchmarks here mostly using dd and ioping to measure disk speeds
Some have 200 / 300 MBs with dd and 3k ipops and other have lower dd results with higher iops .. 100MBs and 10k iops.
I don't know if we can say one is better than other, but in a real world lamp stack, which one would give better results and better response time?
Comments
If dd comes back at under 800 MB/s you need to get a refund!
Then make a complain thread on LET!
Then chargeback.
iops are superior to dd... dd means absolutely nothing, if you enable unsafe writeback caching (or have a RAID card with this function + battery unit) then you'll see near RAM speeds.
The entire >1GB/s dd's because of SSDs are bullshit... No affordable SSD array can naturally produce those kind of numbers. Those are lies, and ioping exposes them... (nobody can cache something in RAM they don't know is going to be requested)
Here is an example.
VPS1:
dd: 355 MB/ss
ioping: 10 requests completed in 9.01 s, 2.25 k iops, 8.78 MiB/s
VPS2:
dd: 86.7 MB/s
ioping: 39.3 k requests completed in 3.0 s, 13.9 k iops, 54.1 MiB/ss
Which one would you choose regarding disk performance only?
VPS2.
VPS 2, look at those nice iops :-)
Sounds like ploop on vps1
Results can be found here. VPS1 is OVH SSD and VPS2 is SSD cache from Rackulous. Any review from the last one?