OS/2, eCS & ArcaOS - Technical > Networking
Moved to UltraFibre 120 Mb/s but OS/2 chugs at 10 Mb/s...???
massimo s.:
i cheked, that line is there
i've
keepalive 120
tcpswinsize 246723
tcprwinsize 246723
updswinsize 246723
udprwinsize 246723
lingertime 60
ipforward 0
mtudiscover 1
firewall 0
etc..
massimo
--- Quote from: David McKenna on June 20, 2018, 11:29:02 pm ---Massimo,
Check inside your C:\TCPIP\BIN\B4TCP.CMD file and make sure it has this:
if exist %etc%\inetcfg.ini CALL inetcfg.exe -set all
If not add it. This command applies the inetcfg.ini file settings when you boot.
Regards,
--- End quote ---
massimo s.:
that line is there
and my ip stack
has theese values
keepalive 120
all the 4 winsize 246723
lingertime 60
ipforward 0
mtudiscover 1
firewall 0
etc...
massimo
--- Quote from: David McKenna on June 20, 2018, 11:29:02 pm ---Massimo,
Check inside your C:\TCPIP\BIN\B4TCP.CMD file and make sure it has this:
if exist %etc%\inetcfg.ini CALL inetcfg.exe -set all
If not add it. This command applies the inetcfg.ini file settings when you boot.
Regards,
--- End quote ---
Dariusz Piatkowski:
Hi Roderick,
--- Quote from: Roderick Klein on June 21, 2018, 01:32:06 am ---If you want to see your machine go down quicker, do turn on SACK. We experimented with this setting at Mensys on some servers and as somebody else already reported, stay far clear from switching it on. It will cause more pain then its worth...
--- End quote ---
Well, I have been running with SACK turned ON since (at least) the Fibre upgrade, so about 8 months now...no problems to report, at least nothing that I am aware of because it creates such a blatant issue.
However, as you and others have pointed out, the OS/2 tcpip stack apparently has a problem with this...so I'm now in the test mode having turned it OFF.
I will monitor for a while and will provide an update later on. Keep in mind, my extent of running a server process is the Web/2 application, nothing else. I suppose any tcpip apps may be impacted by this though, such as Firefox perhaps? So theoretically I should see something eventually...time will tell.
Dariusz Piatkowski:
Hey maxwarp!
--- Quote from: maxwarp@quasarbbs.net on June 20, 2018, 10:55:18 am ---you are lucky
here setting the same values to my stack IP i have no iprovements at all
still 500-600KiloBytes download from Firefox or from wget at the command prompt on my eCS2.1 desktop with an Intel pro 1000 XT PCI-X Nic… binded at gigabit ethernet to my Cisco gigabit ethernet switch
that communicate with my Cisco 8xx router that runs an FTTC 100Mb/sec…. :(
...
guys, any help?
...
--- End quote ---
Yeah, I feel your pain...when it comes to on-line "feel" nothing beats a fast connection speed and when it's not there it gets pretty frustrating.
OK, so a couple of things:
1) various test servers will be impacted by your local tcpip stack settings, for example, take the SACK flag...as I mentioned in my response to Roderick, I did shut it off right now to test it out, the immediate impact => speedtest.net DIES!!! I get a burst of full speed for about 2-3 secs then the traffic completely stops...judging by this result alone I would be inclined to say that having SACK OFF is a mistake...yet hitting several of the other test servers shows no impact, so your results will vary
2) this is a bit of a follow-up to the idea above, but as applicable to the bigger internet picture...you will get different speeds from different servers, so just because I can do 10 Mbyte to my local test server (same city actually) it does not mean that a server somewhere in China or EU for that matter will show the same results...network latency adds up, etc, etc
3) now to be more specific, can you test what you are seeing using another machine on your LAN? For example, in my testing I was attempting to debug the OS/2 issue but my other boxes (Win7 and mobile devices) were showing decent results...is that the case for you as well? If yes, then indeed, the problem appears to lie with the OS/2 setup itself, if no, then it may very well exist outside of your LAN and on the WAN side
4) there are some more in-depth tools you could use, take a look at the port of Wireshark (https://os2ports.smedley.id.au/index.php?page=wireshark) that Paul Smedley did, it will allow you to visually inspect your tcpip stack traffic and may highlight where your OS/2 specific configuration issue lies, great tunning aid, a bit of a learning curve, you need to capture a tcpip trace on your OS/2 machine then pull this into the Wireshark app, not complex at all, but if you're never done it you just have to try it out a couple of times (look up the thread we had on this forum regarding this, great discussion), heck, that could be a great general discussion of how to tune the OS/2 tcpip stack and maybe deserves a separate thread?
Roderick Klein:
--- Quote from: Dariusz Piatkowski on June 22, 2018, 03:46:55 pm ---
1) various test servers will be impacted by your local tcpip stack settings, for example, take the SACK flag...as I mentioned in my response to Roderick, I did shut it off right now to test it out, the immediate impact => speedtest.net DIES!!! I get a burst of full speed for about 2-3 secs then the traffic completely stops...judging by this result alone I would be inclined to say that having SACK OFF is a mistake...yet hitting several of the other test servers shows no impact, so your results will vary
--- End quote ---
The advise is based on the first download server that Mensys ever put online for downloads for eCS. I managed 4 servers running OS/2 in a large datacenter with 100 megabit uplink. And with a lot of traffic you could get the TCP/IP stack to get exhaust the system its memory in about 30 minutes by switching SACK on. There is clearly a bug in the stack! Hence the comment on the inetcfg.ini of eCS to *never* turn it on.
Roderick
Navigation
[0] Message Index
[#] Next page
[*] Previous page
Go to full version