Ask Slashdot: What Is an Acceptable Broadband Latency?

← Back to Stories (view on slashdot.org)

Ask Slashdot: What Is an Acceptable Broadband Latency?

Posted by timothy on Tuesday March 6, 2012 @05:26AM from the insert-rant-about-3g-dongle-speeds dept.

holmedog writes "A simple question with a lot of answers (I hope). I recently had issues with my DSL broadband at home, and after a month of no resolution, I was told 300ms latency (to their test servers) was the acceptable range for Centurylink 10.0Mbps. This got a shocked reaction out of me to say the least. I would think anything over 125ms to be in the unacceptable range. So, I have come to you to ask: What do you consider to be acceptable broadband latency and why?"

18 of 396 comments (clear)

Min score:

Reason:

Sort:

Latency by Anonymous Coward · 2012-03-06 05:28 · Score: 5, Informative

I used to work for AT&T Uverse and over 200ms was enough to get a tech onsite to look at the problem.
1. Re:Latency by Anonymous Coward · 2012-03-06 05:44 · Score: 5, Informative
  
  Your comment assumes that all the devices and media between locations were functioning properly. Latency can also be caused by bad wiring, bad modem, etc. Hell, even line noise can cause it because the line noise forces re-transmits.
2. Re:Latency by gknoy · 2012-03-06 05:48 · Score: 4, Informative
  
  No, but if you point out that the latency between everything up to your street is low, and you have massive latency over the last two hops, it helps show them that something isn't normal.
3. Re:Latency by rogueippacket · 2012-03-06 05:52 · Score: 5, Informative
  
  More often than not, latency is caused by congestion and not number of hops. Hops do introduce latency, but few modern applications need to go very far. So, whether the customer intentionally (bit-torrent) or unintentionally (malware) introduced this congestion is the first thing a tech will check for - usually by disconnecting the local network and running a speed-test directly from a laptop. The latency could also be caused by a local wireless network which is saturated, underpowered, or experiencing interference. So if the wireline speed-test passes, a wireless speed-test is likely to happen next with the tech standing right beside the modem.
  In the much more unlikely scenario that the latency is being introduced by the network itself, the technician will usually escalate the problem and check both the street-side cabinet (DSLAM in this case), and customer profile at the B-RAS deep inside the provider network. It is not uncommon to see a low-speed DSL profile applied to a poor quality local loop, or for the wrong Layer 3 profile to be applied by provisioning error on the B-RAS itself. Both scenarios would result in poor performance for the user, leading to congestion and therefore, latency.
4. Re:Latency by mikael_j · 2012-03-06 06:00 · Score: 4, Informative
  
  Yeah, I used to do tech support and anything over 100 ms or so for the first hop outside the ISP's network was likely to be escalated to a 3rd line tech if we couldn't solve it.
  Hell, right now I'm getting approximately 100-120 ms pings against random machines in the US northeast and around 190-200 ms for the west coast and I'm in northern Sweden...
  
  --
  Greylisting is to SMTP as NAT is to IPv4
5. Re:Latency by Anonymous Coward · 2012-03-06 06:54 · Score: 3, Informative
  
  no, traceroute on linux uses UDP by default (you can make it use ICMP) whereas on Windows its ICMP only.
6. Re:Latency by Anonymous Coward · 2012-03-06 06:57 · Score: 2, Informative
  
  Not all routers will show as "hops"
  If your packets are traversing mpls networks etc then you wont see a lot of the actualy hops
7. Re:Latency by crafty.munchkin · 2012-03-06 08:14 · Score: 5, Informative
  
  You may think it's too specific however it's highly relevant information and should've been in the summary... if it's the third hop, there's nothing you can do at your place to fix it, and most of the above comments are redundant. This issue needs to be escalated within their networks team... *sigh*
  
  --
  ... wait, what?
8. Re:Latency by Forty+Two+Tenfold · 2012-03-06 10:05 · Score: 1, Informative
  
  Actually, simple ping will show you that.
  
  --
  Upward mobility is a slippery slope - the higher you climb the more you show your ass.
9. Re:Latency by Forty+Two+Tenfold · 2012-03-06 11:16 · Score: 4, Informative
  
  Actually, you're wrong. It won't.
  Yes it will:
  
  PING slashdot.org (216.34.181.45) 56(84) bytes of data.
  64 bytes from slashdot.org (216.34.181.45): icmp_seq=1 ttl=239 time=144 ms
  64 bytes from slashdot.org (216.34.181.45): icmp_seq=2 ttl=239 time=140 ms
  64 bytes from slashdot.org (216.34.181.45): icmp_seq=3 ttl=239 time=139 ms
  Now go read about TTL and apologize.
  
  --
  Upward mobility is a slippery slope - the higher you climb the more you show your ass.
Depends... by AdamTrace · 2012-03-06 05:32 · Score: 3, Informative

What are you using your connection for?
If you're sending emails, then 300 is perfectly fine.
Turn based games would be fine. Real time games would be rough.
1. Re:Depends... by sociocapitalist · 2012-03-06 05:55 · Score: 2, Informative
  
  300ms is the serialization delay on a 56kbps modem. Doing any modern email with any sizable attachment would be painful at best and would more likely experience timeouts. Browsing the web with 300ms of delay would be painful.
  Keeping in mind that this delay is apparently inside his ISP network I think that there is no reason that he should accept 300ms unless his ISP is an inter-island carrier and the test servers are on another island or something.
  
  --
  blindly antisocialist = antisocial
It all depends on distance... by BagOBones · 2012-03-06 05:33 · Score: 3, Informative

I can't see 300ms being acceptable anywhere in North America unless you are on a satellite link, however if you are testing over continents then yes.
Testing to the providers own test servers within the same country seems insane to be that high.

--
EA David Gardner -"... but the consumers have proven that actually what they want is fun."
Re:Escalate your trouble ticket by glop · 2012-03-06 05:39 · Score: 3, Informative

Yup, I'd say 10ms is not uncommon for modern
The FCC Says:
Results by ISP. The highest average round-trip latency among ISPs
was 75 ms, while the lowest average latency was 14 ms.
This is from "Measuring Broadband America - FCC" found on the FCC website.
Re:300 Acceptable? by AvitarX · 2012-03-06 05:41 · Score: 5, Informative

I consider anything past 80ms to be slow for my cable connection (to 8.8.8.8).
I just tested 19,17,18,18
I previous test had a 60 something thrown in. This is via a boring home VPN router, shared connection, but under a dozen, and all light users.
13 hops to 8.8.8.8 from here.
33,34,33,63 to /.
300 is what I get on hotel wifi, or my cellphone (to be fair, on my cell phone it goes up to 1000), as can hotel wifi become unusable, I swear most hotels must have 300+ rooms sharing a T1 line.

--
Wow, sent an e-mail as suggested when clicking on "use classic" banner, and got a fast response that addressed my msg
Working at an ISP by andydouble07 · 2012-03-06 05:48 · Score: 3, Informative

I just averaged together the data for a few thousand DSL circuits, and it seems that the average response time is in the area of 65 ms. Anything above 150ms is out of the ordinary. There are even a few CenturyLink circuits in there (reseller), and the average response time for those is a little higher, around 70 ms. Usually slow response times are because of an over-utilized circuit, but if that's not an issue here, then you should probably check the signal and margins on your modem or have CenturyLink send a tech to do so.
Re:300 Acceptable? by DamonHD · 2012-03-06 05:56 · Score: 4, Informative

Generally 1ms or less.
Pinging one of my servers in co-lo on the other side of London and traversing my moderate-speed (~4Mbps/1Mbps) ASDL only takes just over 14ms round-trip.
Pinging my server in the US gives ~110ms.
Singapore: ~270ms.
Sydney, Australia: ~310ms.
So I can get right round the globe and back in about 300ms, *starting* the trip over ADSL.
Rgds
Damon
Rgds
Damon

--
http://m.earth.org.uk/
Re:Latency has a couple of sources... by DamnStupidElf · 2012-03-06 06:57 · Score: 3, Informative

If your ISP won't help and you don't mind adding an additional gateway to your network you can generally fix bufferbloat by traffic-shaping your own traffic on a NAT router with custom firmware or even a PC running *nix. Drop upstream packets that exceed your average upstream, and drop inbound packets exceeding your average downstream (which can change throughout the day, making it kind of difficult to find the right limit). TCP/IP will handle the rest.