dslreports logo
site
 
    All Forums Hot Topics Gallery
spc

spacer




how-to block ads


Search Topic:
uniqs
13
share rss forum feed


TSI Marc
Premium,VIP
join:2006-06-23
Chatham, ON
kudos:28

1 edit
reply to derekm

Re: Google DNS versus ours

yeah but that doesn't lead to better performance.. you want records that are accurate to stay cached so their response is fast.. having to go query the auth dns server where the records are hosted is the part that takes the longest...

sometimes this is why larger dns servers may perform better since they have more queries cached by virtue of simply having more people use it... in that way they dont need to delay while it fetches the record, somebody else has already done that in some cases so to you it appears quicker. typically that's where people might argue that its better.

at our size now though I'd say that's fairly moot but to me that's the only real legitimate thing one could say.. the more users use our servers.. the less of an issue that is too..
--
Marc - CEO/TekSavvy

The Mongoose

join:2010-01-05
Toronto, ON
I caught this thread and decided to re-run namebench...a while back I was having some trouble and switched everything over to Google DNS. Today's test results:

Fastest: TekSavvy
2nd: UltraDNS (31% slower than TSI)
3rd: Primus (35% slower)

Other notables...OpenDNS was 37% slower, Google DNS was 48% slower.

I've switched back to TekSavvy's servers as a result, so far working fine.


HiVolt
Premium
join:2000-12-28
Toronto, ON
kudos:21
reply to TSI Marc
I'll switch back to the TSI servers and see how they perform now...


fluffybunny

@teksavvy.com
reply to TSI Marc
hmm..i get much worse performance with teksavvy DNS than with google :
using GRC nameserver benchmark :

206.248.142.222 | Min | Avg | Max |Std.Dev|Reliab%|
----------------+-------+-------+-------+-------+-------+
- Cached Name | 0.000 | 0.016 | 0.081 | 0.021 | 100.0 |
- Uncached Name | 0.055 | 0.196 | 0.514 | 0.111 | 100.0 |
- DotCom Lookup | 0.077 | 0.163 | 0.272 | 0.052 | 98.0 |
------+-------+-------+-------+-------+-------+

vs

8.8.8.8 | Min | Avg | Max |Std.Dev|Reliab%|
----------------+-------+-------+-------+-------+-------+
+ Cached Name | 0.000 | 0.019 | 0.082 | 0.023 | 100.0 |
+ Uncached Name | 0.047 | 0.165 | 0.440 | 0.101 | 100.0 |
+ DotCom Lookup | 0.048 | 0.166 | 0.283 | 0.060 | 100.0 |
------+-------+-------+-------+-------+-------+


derekm

join:2008-02-26
kudos:1
reply to TSI Marc
said by TSI Marc:

yeah but that doesn't lead to better performance.. you want records that are accurate to stay cached so their response is fast.. having to go query the auth dns server where the records are hosted is the part that takes the longest...

Understood. It wasn't to suggest it would improve performance. It would improve accuracy though. It's a trade off.

If it's 100-500ms (500 would be terrible) every 10-60 minutes that get hit with the latency, I don't think it would even be noticeable, if you look at the average response time.

Also, the end-users computer would respect the TTL in its DNS cache, so it would only be new requests.

You could override this TTL cap for the top 1% of the queries, fairly easily, which would give you better performance for most sites, and better accuracy for the 'long tail'.

Just throwing some (unrequested) ideas out there.


TSI Marc
Premium,VIP
join:2006-06-23
Chatham, ON
kudos:28
yep. that's sort of how this is.. you kind of have to find a good balance based on the load that's on our servers.. there's no one size fits all kind of solution.

thanks for the input.
--
Marc - CEO/TekSavvy


TSI Gabe
Router of Packets
Premium,VIP
join:2007-01-03
Gatineau, QC
kudos:7
reply to fluffybunny
Much worse?

the Cached avg response time is lower for us and the std deviation is also lower.

The uncached is faster for Google by 9ms but still something seems odd with this report as the overall response times are much higher than what I would normally expect on a normal Internet Connection.

I don't know GRC that well...it runs on Windows it looks like
--
TSI Gabe - TekSavvy Solutions Inc.
Authorized TSI employee ( »TekSavvy FAQ »Official support in the forum )


TSI Gabe
Router of Packets
Premium,VIP
join:2007-01-03
Gatineau, QC
kudos:7
Alright, all servers are in production now

»tinyurl.com/9z899t3

Comparing our servers, 206.248.154.22 and 206.248.154.170 to OpenDNS and Google

And the clear winner is us
--
TSI Gabe - TekSavvy Solutions Inc.
Authorized TSI employee ( »TekSavvy FAQ »Official support in the forum )


TSI Gabe
Router of Packets
Premium,VIP
join:2007-01-03
Gatineau, QC
kudos:7
I should probably add that this test is being run from my house from a normal DSL connection, this isn't something that's being run right next to the server that would yield an unfair advantage.

jstory

join:2011-02-05
New Westminster, BC
Here on the we(s)t coast, Google's DNS is the clear winner.

dig teksavvy.com @8.8.8.8
shows a query time of 25 msec.

whereas,

dig teksavvy.com @206.248.142.222
shows a query time of 74 msec


TSI Gabe
Router of Packets
Premium,VIP
join:2007-01-03
Gatineau, QC
kudos:7
That's because Vancouver has separate DNS servers.

You need to use 76.10.191.198 & 199

jstory

join:2011-02-05
New Westminster, BC
Just did.

Got a query response time of 76 msec and 75 msec, respectively, compared to 33 msec for 8.8.8.8.

mtr reports a ping of 13 msec, so maybe the server is just under heavy load.


TSI Marc
Premium,VIP
join:2006-06-23
Chatham, ON
kudos:28
said by jstory:

Just did.

Got a query response time of 76 msec and 75 msec, respectively, compared to 33 msec for 8.8.8.8.

mtr reports a ping of 13 msec, so maybe the server is just under heavy load.

Gabe responded to you earlier. you have to use the Vancouver DNS servers since you're in BC..

That's because Vancouver has separate DNS servers.

You need to use 76.10.191.198 & 199 (these servers are not yet updated though)

we too can make our IPs respond no matter where you are but we just haven't done that.. there's no real need.

Google has that 8.8.8.8 block anycasted.. it's a routing trick.. that make all the routers think that IP is really close but in fact there are srvers everywhere with the same IP...
--
Marc - CEO/TekSavvy


Guspaz
Guspaz
Premium,MVM
join:2001-11-05
Montreal, QC
kudos:23

1 recommendation

said by TSI Marc:

Google has that 8.8.8.8 block anycasted.. it's a routing trick.. that make all the routers think that IP is really close but in fact there are srvers everywhere with the same IP...

There's no reason TSI couldn't anycast the DNS server IPs so that the same DNS IPs are used anywhere in TSI's territory :P Of course, that's kind of pointless since the vast majority of people use DHCP/PPPoE to automatically set the DNS servers anyhow. Most of the people setting theirs by hand are DNS ricers :P
--
Developer: Tomato/MLPPP, Linux/MLPPP, etc »fixppp.org


TSI Marc
Premium,VIP
join:2006-06-23
Chatham, ON
kudos:28
well.. there is one good reason.. and well, it's that it would take a bit of lifting to do it and make sure it's done right and for what? not much value..

we'd have to move everything else off that class C...
--
Marc - CEO/TekSavvy