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.
Comments
Let's join in... Texas Internap optimized bandwidth, from Cloud Shards VPS:
Download speed from CacheFly: 87.4MB/s
Download speed from Linode, Atlanta GA: 13.9MB/s
Download speed from Linode, Dallas, TX: 105MB/s
Download speed from Linode, Tokyo, JP: 6.43MB/s
Download speed from Linode, London, UK: 5.24MB/s
Download speed from Leaseweb, Haarlem, NL: 10.7MB/s
Download speed from Softlayer, Singapore: 6.09MB/s
Download speed from Softlayer, Seattle, WA: 30.0MB/s
Download speed from Softlayer, San Jose, CA: 30.5MB/s
Download speed from Softlayer, Washington, DC: 34.0MB/s
Yes, that should be expected for close/same DC/city locations even for a VPS on a shared 1 gbps port.
It is my expectation as a customer and if it does not work at least a few times (passing 100 mbps i mean) I ask the host what is wrong.
At times the port is 1 gbps but the VPSes themselves are limited to 100 mbps (we have this case in our KVM storage plans) and I am OK with that as a customer also. It makes sure no abuser saturates the port, but there are disadvantages also...
Never needed more than 100 mbps, my home connection is at about 50 and never felt i need more, for professional usage, tho, there are colocation and HEBs, in general, people that offer tons of traffic dont offer high bursts too, that is because the VPSes there use the traffic and saturate the port somewhat, while having 1 gbps with fixed traffic allows for big bursts but for a short time since the alloted traffic will end up quickly since they are not much usually and the port will be free again.
Lots of sad a%% no throughput speed tests.
@concerto49, those speeds are on gigabit? Atlanta is slow by that 100 speed. Seattle, ditto. DC, yep the same.
Internap isn't the miracle network folks make it out to be.
Sorry, those were old results. Forgot a few extra providers were added to the mix lately. I've updated the post.
Atlanta seems to be slow. Will definitely raise an issue on it.
What was up with San Jose on that test too?
The old results didn't have above.net and a few other providers. It was ran months ago. I just re-ran it.
Oh alright, makes sense
@KernelSanders @pubcrawler
Someone needs to tell Linode to fix themselves. It's not Internap's problem. Just tested a few other DCs. And then using RamNode's test file:
me@tx:~# wget test.atl.ramnode.com/100MB.test
--2013-01-27 08:06:59-- http://test.atl.ramnode.com/100MB.test
Resolving test.atl.ramnode.com (test.atl.ramnode.com)... 199.241.28.6
Connecting to test.atl.ramnode.com (test.atl.ramnode.com)|199.241.28.6|:80... connected.
HTTP request sent, awaiting response... 200 OK
Length: 104857600 (100M) [text/plain]
Saving to: `100MB.test'
100%[======================================>] 104,857,600 32.5M/s in 3.1s
2013-01-27 08:07:02 (32.5 MB/s) - `100MB.test' saved [104857600/104857600]
Clearly, it appears the problem is with Linode Texas.
All fairness Linode isn't such a hot place to speed test either. Varies greatly.
Problem we all tend to have here is the common VPS speed test script bundles these tests. So, likely that these same providers get pummeled and slow down entire subnets at times. Certainly, I would do that if I were them.
It is time to update these scripts and common testing points with more diverse mix.