Comments on: DNS vendor performance

By: Adam

Adam — Wed, 15 Jul 2009 23:35:25 +0000

I’m looking at DNS providers to setup failover between two data centres, so very interesting post. Thanks!

My Pingdom trial account is now busily running a DNS 1 minute test for our current rackspace NDS server. I’ll give it a few days and might come back here with the numbers.

BTW – Dynect and Dnsmadeeasy are the only ones mentioned here to employ the anycast technology. I think that should count in their favour?

Even though DynDNS is tun by the same company as Dynect, it is a lower feature service and does not use anycast as far as I understand.

By: DNS performance redux | StyleFeeder Tech Blog

DNS performance redux | StyleFeeder Tech Blog — Mon, 06 Jul 2009 16:58:13 +0000

[...] we noticed some room to improve our DNS numbers, which I mentioned in a post last April. Shortly thereafter, I met up with Jeremy Hitchcock from [...]

By: Dharmesh Shah

Dharmesh Shah — Mon, 13 Apr 2009 04:12:45 +0000

It would also be interesting to test eNOM as well.

That’s where HubSpot (and many related sites) were hosting their DNS for a while, before we switched to DNSMadeEasy for some of it.

You can use http://OnStartups.com for your test, if you’d like.

By: Chris

Chris — Sun, 12 Apr 2009 19:36:05 +0000

Thanks for a helpful report!

It would be interesting to see this study expanded to include some of the registrars like GoDaddy that offer DNS.

By: Philip Jacob

Philip Jacob — Sun, 12 Apr 2009 17:10:26 +0000

Yes, the probes that are measuring performance here are using Pingdom. The locations that Pingdom use are on their site which today are listed as:

1 Vasteras, Sweden s15.pingdom.com 212.247.189.113
2 Herndon, VA s403.pingdom.com 207.97.207.200
3 Dallas 4, TX s402.pingdom.com 67.192.120.134
4 London, UK s401.pingdom.com 78.136.27.223
5 Montreal, Canada s34.pingdom.com 67.205.112.79
6 Houston 2, TX, USA s33.pingdom.com 174.133.253.162
7 Stockholm, Sweden s238.pingdom.com 83.140.19.38
8 Reading, England s31.pingdom.com 89.151.110.152
9 Dallas 3, TX, USA s25.pingdom.com 209.62.54.130
10 Berkeley, CA, USA s16.pingdom.com 72.51.41.47
11 Paris, France s404.pingdom.com 62.193.228.125

By: Jeremy Hitchcock

Jeremy Hitchcock — Sat, 11 Apr 2009 19:35:01 +0000

Cool comparison, I love to see objective measures on DNS performance. I expect a lot more of this in the future which is great for all of the service providers to see where to improve. Users’ tolerance for latency is a pretty logarithmic which is going to push us even faster. Like John’s report, it’s the Pingdom DNS test? Where are they testing from and how are they averaging?

The Dynect Platform and DynDNS.com are indeed run by the same company but they are really different services. There’s some truth on value discussion for Dynect Platform v. DynDNS/Custom DNS for smaller sites. In the end we think we have both covered.

One thing not highlighted on the Pingdom report is overall availability of DNS services. DynDNS/Custom DNS has been running since 2001 with no outages. Since then, we’ve picked some pretty cool sites, a number of TLDs, and built out a new network with the TLDS/enterprise customers on the Dynect Platform.

By: Philip Jacob

Philip Jacob — Fri, 10 Apr 2009 12:54:43 +0000

Not anymore! Thanks for letting me know.

By: Yoav Shapira

Yoav Shapira — Fri, 10 Apr 2009 12:33:58 +0000

Useful data! Thanks for sharing ;) And we don’t mind being part of your benchmark at all.

BTW, the link to HubSpot is broken, missing “.com” at the end of the href ;)