| reply to Oedipus
Re: [Speed] Comcast Business Class Speed Upgraded in California Guys, guys, calm down. Powerboost is still there. It's the speedtest.comcast.net that's changed. (And it changed awhile back, not as part of these changes). It downloads/uploads for longer and that means a larger percentage of the test happens at non powerboosted speeds - therefore it reports a lower result. A phone/tablet maxing out a WiFi connection at optimal conditions can still result in a very high Mbps speedtest because they haven't changed the app on mobile devices to use the larger data payload that the website based ones do. |
|
|
|
 EGThe wings of lovePremium
join:2006-11-18
Union, NJ
kudos:9 | Withdrawn. Mods please delete. |
|
| reply to ualdayan
said by ualdayan:Guys, guys, calm down. Powerboost is still there. It's the speedtest.comcast.net that's changed. (And it changed awhile back, not as part of these changes). It downloads/uploads for longer and that means a larger percentage of the test happens at non powerboosted speeds - therefore it reports a lower result. A phone/tablet maxing out a WiFi connection at optimal conditions can still result in a very high Mbps speedtest because they haven't changed the app on mobile devices to use the larger data payload that the website based ones do.
In their defense, ShaperProbe numbers were posted earlier, which splits the PB/non-PB results.
As for the Comcast test, in my recent experience, it still greatly skews results towards best-case PB speeds. I just ran a test a couple of minutes ago and hit 75 Mbps down, before dropping to 23 at about 80% through it. It reported 67.2 Mbps down at the end of it. I suppose that's understandable considering it dropped off near the end of it. However, it reported 22.36 Mbps up, even though my upstream PB ran out at about 40% through that part of the test and dropped to 5 Mbps for the rest of it.
I typically use the Comcast speedtest to check for local/regional congestion (and e-peen numbers  ), and ShaperProbe to check for provisioning and sustained throughput. Sometimes I also do an FTP upload to my website to check sustained upstream speeds.
While I find the variance in PB reported earlier to be odd/interesting (ex. ropeguru  's results are pretty close to residential Blast PB), I wouldn't mind it much myself if it got reduced. I was on 50/10 until mid-August, and I didn't mind the complete lack of it there.
--
KI6RIT |
|
 ropeguruPremium
join:2001-01-25
Mechanicsville, VA | reply to ualdayan
said by ualdayan:Guys, guys, calm down. Powerboost is still there. It's the speedtest.comcast.net that's changed. (And it changed awhile back, not as part of these changes). It downloads/uploads for longer and that means a larger percentage of the test happens at non powerboosted speeds - therefore it reports a lower result. A phone/tablet maxing out a WiFi connection at optimal conditions can still result in a very high Mbps speedtest because they haven't changed the app on mobile devices to use the larger data payload that the website based ones do.
Cannot say that is true here. I do not get the initial burst at all even on the Comcast speedtest. As late as this weekend I was still seeing the high burst rates, 70+/10+, no matter what Comcast test I hit. Additionally, shaper probe is no longer showing the higher burst ratee that I was seeing before.
So they have screwed something up when rolling out the speed increases. At least here in this area.
Capacity estimation before:
Estimating capacity:
Upstream: 20946 Kbps.
Downstream: 129069 Kbps.
Capacity estimation now:
Estimating capacity:
Upstream: 7700 Kbps.
Downstream: 36244 Kbps. |
|
| said by ropeguru:said by ualdayan:Guys, guys, calm down. Powerboost is still there. It's the speedtest.comcast.net that's changed. (And it changed awhile back, not as part of these changes). It downloads/uploads for longer and that means a larger percentage of the test happens at non powerboosted speeds - therefore it reports a lower result. A phone/tablet maxing out a WiFi connection at optimal conditions can still result in a very high Mbps speedtest because they haven't changed the app on mobile devices to use the larger data payload that the website based ones do.
Cannot say that is true here. I do not get the initial burst at all even on the Comcast speedtest. As late as this weekend I was still seeing the high burst rates, 70+/10+, no matter what Comcast test I hit. Additionally, shaper probe is no longer showing the higher burst ratee that I was seeing before. So they have screwed something up when rolling out the speed increases. At least here in this area. Capacity estimation before: Estimating capacity: Upstream: 20946 Kbps. Downstream: 129069 Kbps. Capacity estimation now: Estimating capacity: Upstream: 7700 Kbps. Downstream: 36244 Kbps. Hmm, maybe all the business line owners are rebooting their modems and running speed tests at the moment in your area? : ) |
|
 JohnInSJPremium
join:2003-09-22
San Jose, CA
 ·PHONE POWER
 ·Comcast
| reply to greg925
rebooted this morning in san jose
12/2 is now
Upstream: No shaper detected.
Median received rate: 3397 Kbps.
Downstream: Burst size: 9843-9962 KB; Shaping rate: 17024 Kbps.
17/3 - nice.
Not sure why it didn't see a speedboost on the uplink.
--
My place : »www.schettino.us |
|
 pflogBueller? Bueller?Premium,MVM
join:2001-09-01
El Dorado Hills, CA
kudos:3 | reply to ropeguru
said by ropeguru:said by ualdayan:Guys, guys, calm down. Powerboost is still there. It's the speedtest.comcast.net that's changed. (And it changed awhile back, not as part of these changes). It downloads/uploads for longer and that means a larger percentage of the test happens at non powerboosted speeds - therefore it reports a lower result. A phone/tablet maxing out a WiFi connection at optimal conditions can still result in a very high Mbps speedtest because they haven't changed the app on mobile devices to use the larger data payload that the website based ones do.
Cannot say that is true here. I do not get the initial burst at all even on the Comcast speedtest. As late as this weekend I was still seeing the high burst rates, 70+/10+, no matter what Comcast test I hit. Additionally, shaper probe is no longer showing the higher burst ratee that I was seeing before. So they have screwed something up when rolling out the speed increases. At least here in this area. Capacity estimation before: Estimating capacity: Upstream: 20946 Kbps. Downstream: 129069 Kbps. Capacity estimation now: Estimating capacity: Upstream: 7700 Kbps. Downstream: 36244 Kbps. I am seeing the same thing. Very little or no power boost now. And the shaping is not smooth at all for the sustained rate. I'm actually all for zero power boost if the shaping were smooth for the 27/7 rates, as it would let me do proper QoS and not have to deal with powerboost funkiness. But it seems the boost is kinda/sorta there, but misconfigured, or the shaping for the 27/7 is not quite tweaked properly.
Perhaps SteveTeow can shed some light?
--
"Women. Can't live with 'em, pass the beer nuts." -Norm |
|
pflogBueller? Bueller?Premium,MVM
join:2001-09-01
El Dorado Hills, CA
kudos:3 | Actually, I take that back. I am seeing ~65 Mbps boost now. Previously I was seeing 100+. So that's still there, just not as much. I'm fine with that, although I still wish there was a way to opt out of powerboost entirely. 
quote:
Upstream: No shaper detected.
Median received rate: 7242 Kbps.
Downstream: Burst size: 20136-20323 KB; Shaping rate: 28634 Kbps.
--
"Women. Can't live with 'em, pass the beer nuts." -Norm |
|
Reviews:
·Comcast Business..
·VOIPo
 ·DSL EXTREME
| reply to ropeguru
said by ropeguru:said by ualdayan:Guys, guys, calm down. Powerboost is still there. It's the speedtest.comcast.net that's changed. (And it changed awhile back, not as part of these changes). It downloads/uploads for longer and that means a larger percentage of the test happens at non powerboosted speeds - therefore it reports a lower result. A phone/tablet maxing out a WiFi connection at optimal conditions can still result in a very high Mbps speedtest because they haven't changed the app on mobile devices to use the larger data payload that the website based ones do.
Cannot say that is true here. I do not get the initial burst at all even on the Comcast speedtest. As late as this weekend I was still seeing the high burst rates, 70+/10+, no matter what Comcast test I hit. Additionally, shaper probe is no longer showing the higher burst ratee that I was seeing before. So they have screwed something up when rolling out the speed increases. At least here in this area. Capacity estimation before: Estimating capacity: Upstream: 20946 Kbps. Downstream: 129069 Kbps. Capacity estimation now: Estimating capacity: Upstream: 7700 Kbps. Downstream: 36244 Kbps. I'm seeing the same thing here is Silicon Valley. Speeds have been all over the board since yesterday. Sometimes I get 17/3 sometimes I don't even get close to 12/2. PowerBoost seems to come and go. Estimated Capacity is only a small fraction of what it used to be any time I run ShaperProbe.
Here is my latest test. Note I got 17/3 last night:
Shaper Detection Module.
Connected to server 74.63.50.34.
Estimating capacity:
Upstream: 1129 Kbps.
Downstream: 2248 Kbps.
The measurement will take upto 2.5 minutes. Please wait.
Checking for traffic shapers:
Upstream: No shaper detected.
Median received rate: 1120 Kbps.
Downstream: No shaper detected.
Median received rate: 2202 Kbps.
--
Craig
»CraigHarris.org My BLOG on Motorcycles, Computer Stuff & Deals. |
|
pflogBueller? Bueller?Premium,MVM
join:2001-09-01
El Dorado Hills, CA
kudos:3 | reply to greg925
Definitely looks like I've lost power boost on the upstream side, and either all or most of it on the downstream side.
--
"Women. Can't live with 'em, pass the beer nuts." -Norm |
|
 NetFixerFrom my cold dead handsPremium
join:2004-06-24
The Boro
·Comcast Business..
·Vonage
 ·Cingular Wireless
·Comcast
1 edit | reply to JohnInSJ
said by JohnInSJ:rebooted this morning in san jose
12/2 is now
Upstream: No shaper detected.
Median received rate: 3397 Kbps.
Downstream: Burst size: 9843-9962 KB; Shaping rate: 17024 Kbps.
17/3 - nice.
Not sure why it didn't see a speedboost on the uplink.
I randomly see no PowerBoost reported on both the upstream and the downstream when testing with ShaperProbe.
But I would actually like to see Comcast offer a config option to disable PowerBoost anyway. In fact, I usually run through a VLAN segment of my Netgear GS108e switch just behind my cable modem so that I can use its rate limiting QoS capability to compensate for the sometimes extreme buffer bloat effect that the combination of Comcast's PowerBoost and channel bonding sometimes exacerbate. Since the "leak" of Comcast's plan to increase the bandwidth for the two lower business class tiers, I have removed that VLAN connection until I could verify exactly what the new speed tier delivered. Now that I know, I will probably put that rate limiting VLAN segment back into operation.
EDIT:
I just put my rate limiting VLAN segment back into service, and I thought I would post some ICSI Netalyzr results to illustrate why I did it:
Netalyzr results without rate limiting
The 690 ms upstream buffer value above is actually an improvement over the ~1000 ms value I was seeing prior to the rate increase from 2mbps to 3mbps (which makes sense because the improved excess buffering ratio tracks the real bandwidth increase ratio).
Netalyzr results with rate limiting
Here is a link to an ICSI FAQ that explains the effects of excessive buffering (AKA buffer bloat): »n3.netalyzr.icsi.berkeley.edu/in···fer.html
Here is a brief extract from that FAQ:
said by ICSI :
Often, your computer wants to send or receive data faster than some point in the network allows. Thus that point needs a buffer to store this data until it is able to send it. The problem arises when the buffer is too large or too small. If the buffer is too small, network protocols such as TCP are unable to send as fast as the network allows. If the buffer is too large, a single transfer will fill up the buffer, delaying all other traffic.
Currently, a lot of users have networks which are significantly over-buffered. As a result, if the network is running at capacity, packets may be substantially delayed. This is why, for example, BitTorrent may slow down a user's web surfing, even though TCP is able to share all the bandwidth, the file transfer fills up the buffer which now slows down all other traffic.
In other words, those of you who are bemoaning an apparent loss of PowerBoost with the new speed increase, might want to be thankful instead of angry.
--
We can never have enough of nature.
We need to witness our own limits transgressed, and some life pasturing freely where we never wander. |
|
ropeguruPremium
join:2001-01-25
Mechanicsville, VA | reply to pflog
said by pflog:Definitely looks like I've lost power boost on the upstream side, and either all or most of it on the downstream side.
Exactly what I am seeing here.
But as someone else was saying. Just deal with it! J/K |
|
NetFixerFrom my cold dead handsPremium
join:2004-06-24
The Boro Reviews:
·Comcast Business..
·Vonage
·Cingular Wireless
·Comcast
| said by ropeguru:said by pflog:Definitely looks like I've lost power boost on the upstream side, and either all or most of it on the downstream side.
Exactly what I am seeing here. But as someone else was saying. Just deal with it! J/K Or perhaps even be happy about the reduced PowerBoost?
Some of us actually go to the trouble to limit the negative effects of PowerBoost:
»Re: [Speed] Comcast Business Class Speed Upgraded in California
Of course, the universal YMMV disclaimer is always in effect.
--
We can never have enough of nature.
We need to witness our own limits transgressed, and some life pasturing freely where we never wander. |
|
pflogBueller? Bueller?Premium,MVM
join:2001-09-01
El Dorado Hills, CA
kudos:3 | I can understand folks being upset about losing something they had for a long time, especially if their rep told them to expect it.
That said, I for one would much rather have sustained 27/7 with no PB and have it shaped properly, which lets me control things much more on my end via shaping/QoS.
Anyone know of a good consistent host to wget/fetch a file from in California (at least 256 MB) so I can do a pcap capture and see how the throughput graph looks for sustained transfers?
--
"Women. Can't live with 'em, pass the beer nuts." -Norm |
|
| powerboost on buisness is really nice.
Like if you host a bunch of images, it will load faster with the high upload rate for the short period. Especially if those pictures are like 8 megabytes. |
|
JohnInSJPremium
join:2003-09-22
San Jose, CA | Likely it will return. Just give it a few days for them to get the kinks out.
--
My place : »www.schettino.us |
|
ropeguruPremium
join:2001-01-25
Mechanicsville, VA | reply to pflog
said by pflog:I can understand folks being upset about losing something they had for a long time, especially if their rep told them to expect it.
That said, I for one would much rather have sustained 27/7 with no PB and have it shaped properly, which lets me control things much more on my end via shaping/QoS.
Anyone know of a good consistent host to wget/fetch a file from in California (at least 256 MB) so I can do a pcap capture and see how the throughput graph looks for sustained transfers?
Look around at some of the linux mirrors where you can download the DVD. THat will give you a good 4GB worth of data to test with.
I am getting ready for work now but if I have a little time when I get there, I will take a quick look and see if I can find on for ya. |
|
pflogBueller? Bueller?Premium,MVM
join:2001-09-01
El Dorado Hills, CA
kudos:3 | reply to greg925
Picked a local FreeBSD mirror to fetch a large file from, and the speeds start out relatively smoothly shaped. But then the shaping becomes less smooth and it bounces around between slow and fast rather erratically.
Anyone else in California on a 22/5 (now 27/7?) plan who can do a pcap and generate similar data to see if the shaping is broken in other locations as well?
--
"Women. Can't live with 'em, pass the beer nuts." -Norm |
|
 espaethDigital PlumberPremium,MVM
join:2001-04-21
Minneapolis, MN
kudos:2
·Vitelity VOIP
| said by pflog:Anyone else in California on a 22/5 (now 27/7?) plan who can do a pcap and generate similar data to see if the shaping is broken in other locations as well? I don't have the data to post right now, but yes, I'm observing the same behavior in the Minneapolis market. |
|
pflogBueller? Bueller?Premium,MVM
join:2001-09-01
El Dorado Hills, CA
kudos:3 | said by espaeth:said by pflog:Anyone else in California on a 22/5 (now 27/7?) plan who can do a pcap and generate similar data to see if the shaping is broken in other locations as well? I don't have the data to post right now, but yes, I'm observing the same behavior in the Minneapolis market. Ok, cool. I was starting to worry it was my TCP stack, but I've fiddled with a number of things including different congestion control algorithms, etc and am seeing similar results and the fact that it's relatively smooth in the beginning then erratic after the point where powerboost would normally cease tells me it is something on Comcast's end.
I'm guessing they are just ironing out the kinks in the buffering/etc with the new speed profiles?
--
"Women. Can't live with 'em, pass the beer nuts." -Norm |
|
