![]() |
![]() |
|
|||||||
| Register | Forum Rules | Getting Started! - Guide | Blog | Videos | Gallery | Members List | Social Groups | Mark Forums Read |
![]() |
|
|
Thread Tools | Display Modes |
|
|
#1 |
|
Guest
Posts: n/a
|
Speedtest discrepancy
This is an honest technical 'troubleshooting' question, not a 'my
OS/browser/newsreader is better than yours' opportunity. Two ethernet wired lan computers are accessing the internet via a router and cable modem. Pc1 is Win98se + IE6 SP1 and pc2 is Freespire2 + Firefox2.0.0.4. They are performing a browser website speedtest at http://speedtest.nethere.net/ (click here to start test) because that speedtest server is in my geographic area. The Winbox consistently has results in the range 2214 Kbps or 276.76 KB/sec (one example, maybe a little more sometimes), while the linuxbox consistently has results in the range 5895 Kbps or 736.86 KB/sec. I don't understand that. Does anyone have any suggestions about researching the discrepancy? Additional hardware and configurational information available on request. -- Mike Easter |
|
|
|
#2 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
Mike Easter wrote:
> This is an honest technical 'troubleshooting' question, not a 'my > OS/browser/newsreader is better than yours' opportunity. > > Two ethernet wired lan computers are accessing the internet via a router > and cable modem. Pc1 is Win98se + IE6 SP1 and pc2 is Freespire2 + > Firefox2.0.0.4. They are performing a browser website speedtest at > http://speedtest.nethere.net/ (click here to start test) because that > speedtest server is in my geographic area. > > The Winbox consistently has results in the range 2214 Kbps or 276.76 > KB/sec (one example, maybe a little more sometimes), while the linuxbox > consistently has results in the range 5895 Kbps or 736.86 KB/sec. > > I don't understand that. Does anyone have any suggestions about > researching the discrepancy? Additional hardware and configurational > information available on request. > The Linux tcp stack is far better than what Windoze provides. There's your discrepancy. What else do you need to know? Your results have been consistant with everyone else who's bothered to check out this stuff. Cheers. -- Boot It Up! http://youtube.com/watch?v=-kql8cWqiv8 |
|
|
|
#3 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
Mike Easter wrote:
> This is an honest technical 'troubleshooting' question, not a 'my > OS/browser/newsreader is better than yours' opportunity. > > Two ethernet wired lan computers are accessing the internet via a router > and cable modem. Pc1 is Win98se + IE6 SP1 and pc2 is Freespire2 + > Firefox2.0.0.4. They are performing a browser website speedtest at > http://speedtest.nethere.net/ (click here to start test) because that > speedtest server is in my geographic area. > > The Winbox consistently has results in the range 2214 Kbps or 276.76 > KB/sec (one example, maybe a little more sometimes), while the linuxbox > consistently has results in the range 5895 Kbps or 736.86 KB/sec. > > I don't understand that. Does anyone have any suggestions about > researching the discrepancy? Additional hardware and configurational > information available on request. > While that /wide/ a discrepancy seems a bit much, I've seen similar comparisons. In fact, I did one on this machine a long time ago when I was first getting involved with Linux. W2K w/IE6sp1 was substantially slower than whatever Linux I was running at the time with Fx. I was told it has something to do with how each OS handles the TCP stacks or some shit that I know absolutely nothing about. -- Mark Warner SimplyMEPIS Linux v6.5 Registered Linux User #415318 ....lose .inhibitions when replying |
|
|
|
#4 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
Mike Easter wrote:
> This is an honest technical 'troubleshooting' question, not a 'my > OS/browser/newsreader is better than yours' opportunity. > > Two ethernet wired lan computers are accessing the internet via a router > and cable modem. Pc1 is Win98se + IE6 SP1 and pc2 is Freespire2 + > Firefox2.0.0.4. They are performing a browser website speedtest at > http://speedtest.nethere.net/ (click here to start test) because that > speedtest server is in my geographic area. > > The Winbox consistently has results in the range 2214 Kbps or 276.76 > KB/sec (one example, maybe a little more sometimes), while the linuxbox > consistently has results in the range 5895 Kbps or 736.86 KB/sec. > > I don't understand that. Does anyone have any suggestions about > researching the discrepancy? Additional hardware and configurational > information available on request. > Can it have something to do with virusscan on W$ and none on linux ? -- MarcB |
|
|
|
#5 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
NoStop wrote:
> Mike Easter wrote: > >> This is an honest technical 'troubleshooting' question, not a 'my >> OS/browser/newsreader is better than yours' opportunity. >> >> Two ethernet wired lan computers are accessing the internet via a router >> and cable modem. Pc1 is Win98se + IE6 SP1 and pc2 is Freespire2 + >> Firefox2.0.0.4. They are performing a browser website speedtest at >> http://speedtest.nethere.net/ (click here to start test) because that >> speedtest server is in my geographic area. >> >> The Winbox consistently has results in the range 2214 Kbps or 276.76 >> KB/sec (one example, maybe a little more sometimes), while the linuxbox >> consistently has results in the range 5895 Kbps or 736.86 KB/sec. >> >> I don't understand that. Does anyone have any suggestions about >> researching the discrepancy? Additional hardware and configurational >> information available on request. >> > The Linux tcp stack is far better than what Windoze provides. There's your > discrepancy. What else do you need to know? Your results have been > consistant with everyone else who's bothered to check out this stuff. > > Cheers. > Wasn't there a week long flame war on this very topic a month or so back? |
|
|
|
#6 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
Mike Easter wrote:
> The Winbox consistently has results in the range 2214 Kbps or 276.76 > KB/sec (one example, maybe a little more sometimes), while the linuxbox > consistently has results in the range 5895 Kbps or 736.86 KB/sec. This is not uncommon. > I don't understand that. Does anyone have any suggestions about > researching the discrepancy? You don't need to - it's a normal state of affairs. Windoze uses an ancient TCP/IP stack stolen from BSD back in the early nineties. Problem is that they stole the *wrong* version. The one that they've based all their rubbish on was fundamentally broken! The other issues are the silly "Windows Firewall" which does /nothing/ useful, but slows down connections. Also if you have any of the silly anti-malware nonsense running, your net connection will be further crippled... Isn't it nice not to have to worry about "anti-virus", "anti-trojan" and "anti-worm" silliness? C. |
|
|
|
#7 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
clay illuminated alt.os.linux.ubuntu by typing:
> Wasn't there a week long flame war on this very topic a month or so back? Yup. I remember it well. I did a test suggested by NoStop (I think) and was incredibly surprised by the results. Linux gave better results than windows on *every* test. -- Moog "If this is gonna be that kinda party I'm gonna stick my **** in the mashed potatoes" |
|
|
|
#8 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
In <CIuhj.165694$cJ3.75395@fe2.news.blueyonder.co.u k> Christopher Hunter:
[Snip...] > Windoze uses an ancient TCP/IP stack stolen from BSD back in the early > nineties. Problem is that they stole the *wrong* version. The one that > they've based all their rubbish on was fundamentally broken! ....in ways that *CONTINUALLY AND PERPETUALLY* put the entire net at risk: Microsoft Security Bulletin MS08-001 - Critical Vulnerabilities in Windows TCP/IP Could Allow Remote Code Execution (941644) Published: January 8, 2008 Version: 1.0 General Information Executive Summary This critical security update resolves two privately reported vulnerabilities in Transmission Control Protocol/Internet Protocol (TCP/IP) processing. An attacker who successfully exploited this vulnerability could take complete control of an affected system. An attacker could then install programs; view, change, or delete data; or create new accounts with full user rights. This is a critical security update for all supported editions of Windows XP and Windows Vista, an important security update for all supported editions of Windows Server 2003, and a moderate security update for all supported editions of Microsoft Windows 2000. For more information, see the subsection, Affected and Non-Affected Software, in this section. More: http://www.microsoft.com/technet/sec.../MS08-001.mspx This is a huge hole. Even a dumbass hack like Monkey Boy should blush. -- Regards, Weird (Harold Stevens) * IMPORTANT EMAIL INFO FOLLOWS * Pardon any bogus email addresses (wookie) in place for spambots. Really, it's (wyrd) at airmail, dotted with net. DO NOT SPAM IT. Kids jumping ship? Looking to hire an old-school type? Email me. |
|
|
|
#9 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
On Thu, 10 Jan 2008 18:55:43 +0000, clay wrote:
>> The Linux tcp stack is far better than what Windoze provides. There's >> your discrepancy. What else do you need to know? Your results have been >> consistant with everyone else who's bothered to check out this stuff. >> > Wasn't there a week long flame war on this very topic a month or so > back? Well, if it's already been a month, isn't it overdue for a re-run? ;-) |
|
|
|
#10 |
|
Guest
Posts: n/a
|
Re: Speedtest discrepancy
Moog wrote:
> clay illuminated alt.os.linux.ubuntu by typing: > >> Wasn't there a week long flame war on this very topic a month or so back? > > Yup. I remember it well. > > I did a test suggested by NoStop (I think) and was incredibly > surprised by the results. Linux gave better results than windows on > *every* test. > Just rerun it on Vista. "Surprise" would be the least of your feelings. Linux has beaten windows in network throughput since a very long time It is very telling that even Samba running on linux is actually faster than the "real thing". And even that at quite some margin -- No trees were destroyed in the sending of this message, however, a significant number of electrons were terribly inconvenienced. |
|
![]() |
| Thread Tools | |
| Display Modes | |
|
|
< Home - Windows Help - MS Office Help - Hardware Support >
| New To Site? | Need Help? |