Joao, this is my FreeBSD 5.4 STABLE system (~20 Mbit/7K pps traffic, ~400 hosts),
23 processes: 1 running, 22 sleeping CPU states: 23.4% user, 0.0% nice, 2.7% system, 4.3% interrupt, 69.5% idle Mem: 72M Active, 755M Inact, 118M Wired, 52M Cache, 112M Buf, 3736K Free Swap: 2000M Total, 2000M Free PID USERNAME PRI NICE SIZE RES STATE TIME WCPU CPU COMMAND 15026 support 20 0 77788K 67720K kserel 414:02 0.00% 0.00% lt-ntop 362 root 96 0 3476K 2204K select 0:03 0.00% 0.00% sendmail 356 root 96 0 3384K 1788K select 0:00 0.00% 0.00% sshd [..] Luca Joao Barros wrote: >Luca, > >I could get ntop running (and keep it running) on my laptop (i386) but >if you check my 1st email, in which I included a top paste from the >laptop you'll notice CPU states: 12.0% user, 0.0% nice, >>> 80.2% >system <<<, 7.8% interrupt, 0.0% idle >That was with ntop from cvs that day and 5.4RC4 on i386. Do you get >different results on your box? If not do you consider it normal >behavior? > >On 5/10/05, Luca Deri <[EMAIL PROTECTED]> wrote: > > >>Joao, >>I can tell you for sure that FreeBSD 5.4 stable on x86 is the only >>FreeBSD system that IMHO behaves well. I cannot comment about the Sparc >>version you're using. >> >> >>Cheers, Luca >> >>Joao Barros wrote: >> >> >> >>>Luca, >>> >>>ntop was tested on both machines with little traffic, on the ultra5 >>>for example with a ssh connection and the traffic from ntop's webpage >>>only (plus some dns and dhcp). Just by using the webpage I could force >>>the libpcap thread to quit. The low cpu speed of this machine is only >>>relevant to enhance the wicked behavior of ntop on FreeBSD. >>> >>>Regarding FreeBSD's threading, it would be very interesting in getting >>>some of the core developers eyes on this issue. >>> >>>Joao Barros >>> >>>On 5/6/05, Luca Deri <[EMAIL PROTECTED]> wrote: >>> >>> >>> >>>Joao, >>>why is the CPU a problem for you? Because you have little traffic to >>>analyze or because you expect a lighter CPU usage? How did you configure >>>ntop and where (topology, network speed etc)? Bearn in mind that ntop >>>has been designed (default) to monitor a LAN so if you have a WAN or a >>>large network you better configure properly. >>> >>>FreeBSD is definitively not the best OS in terms of threading (although >>>many other things work nicely and probably better than other similar >>>OSs). I have no experience on Sun+BSD, so I cannot really provide you a >>>more precise answer to your problem. >>> >>>Cheers, Luca >>> >>>Joao Barros wrote: >>> >>> >>> >>>>Hi all, 1st post :) >>>> >>>> >>>>I installed ntop from ports on my Sun Ultra5 400MHz running FreeBSD >>>>5.4RC3 and noticed the cpu would go to 100% and stay there (98% ntop >>>>process and load average 1.0). >>>>I could see traffic being analised throught the webpage but poking >>>>around the page would caus e this to happen: ntop[86069]: >>>>THREADMGMT: pcapDispatch thread terminated... >>>>and of course, no more captured packets which ntop would report >>>>correctly on the number of discarded packets by libpcap. >>>>I already read about this in the mailing list archives but tried to >>>>reproduce it on my laptop, a P4m 2.0GHz running FreeBSD 5.4RC4. >>>>Since this cpu is somewhat faster I couldn't get the pcapDispatch >>>>thread to terminate, but still got some packets discarded by libpcap >>>>and yet 100% cpu usage, but this time still with load average at >>>>almost 1.0 but the ntop process low although I see it's pushing for >>>>the kernel. >>>>top after about 5mins after starting ntop: >>>> >>>> >>>>last pid: 61804; load averages: 0.95, 0.54, 0.60 >>>> up 0+03:27:52 06:40:50 >>>>30 processes: 2 running, 28 sleeping >>>>CPU states: 12.0% user, 0.0% nice, 80.2% system, 7.8% interrupt, >>>> >>>> >>>0.0% idle >>> >>> >>>>Mem: 47M Active, 111M Inact, 40M Wired, 68K Cache, 34M Buf, 40M Free >>>>Swap: 400M Total, 400M Free >>>> >>>> >>>> PID USERNAME PRI NICE SIZE RES STATE TIME WCPU CPU COMMAND >>>>61801 nobody 123 0 47304K 33040K RUN 2:36 39.07% 39.06% ntop >>>> >>>> >>>>Notice the 80% used by system. >>>> >>>> >>>>I tried ntop 3.1 from ports on both systems and 3.1.1 from cvs today >>>>on the laptop, both with the same results. >>>> >>>> >>>>quoting Burton: >>>>"However, I'm not all that comfortable changing the basic daemonizing >>>> >>>> >>>logic >>> >>> >>>>w/o a lot of testing - that's why we held off - it was too close to 3.0's >>>>release on that change. >>>> >>>> >>>>Maybe it is time to try this - but only if we can get people to commit to >>>>trying the cvs. The results from the last few requests for help >>>> >>>> >>>testing has >>> >>> >>>>been resounding silence." >>>> >>>> >>>>I'm willing to test anything you through at me, so please do :) >>>> >>>> >>>>My thanks in advance, >>>> >>>> >>>>Joao Barros >>>>_______________________________________________ >>>>Ntop mailing list >>>>[email protected] >>>>http://listgateway.unipi.it/mailman/listinfo/ntop >>>> >>>> >>-- >>Luca Deri <[EMAIL PROTECTED]> http://luca.ntop.org/ >>Hacker: someone who loves to program and enjoys being >>clever about it - Richard Stallman >> >> >> >> >_______________________________________________ >Ntop mailing list >[email protected] >http://listgateway.unipi.it/mailman/listinfo/ntop > > -- Luca Deri <[EMAIL PROTECTED]> http://luca.ntop.org/ Hacker: someone who loves to program and enjoys being clever about it - Richard Stallman _______________________________________________ Ntop mailing list [email protected] http://listgateway.unipi.it/mailman/listinfo/ntop
