Thread: Re: [bwm-tools-tech] Configuration
Brought to you by:
nkukard
Menu
▾
▴
bwm-tools-tech
|
From: Nigel K. <nk...@lb...> - 2006-07-25 16:26:17
Attachments:
signature.asc
|
> Ok changed IPQ_BUFSIZE to 16384 and recompiled and it seems to be worki= ng > for the last 5 minutes without any errors. Will keep you posted. Cool .... only drawback is bwm will now eat ram like its going out of fashion ... not tooo bad though, I'll try address the problem in the next development release. >=20 > Please advise if you want me to do anything else on the box. >=20 > CPU usage is also around 1-3% only. Great ... >=20 > Thanks very much for your help. >=20 > What are the limitations of bwm? I will be playing around with the grap= hing > utilities and will get back to you in case of any problems. Well ... I've tried it out on a switched Gbit network and managed to fully saturate the network cards ... on a celeron D 2.8 it pulled about 30% CPU. I would also recommend you maybe increase your ip_queue size to 32768 or something, just incase something else munches CPU and bwm is unable to keep up .... I'm also looking at renicing bwm to give it high priority aswell. -Nigel >=20 > Thanks again. >=20 > Regards > Ravi=20 >=20 > -----Original Message----- > From: Nigel Kukard [mailto:nk...@lb...]=20 > Sent: Tuesday, July 25, 2006 8:29 PM > To: ra...@sw... > Subject: Re: [bwm-tools-tech] Configuration >=20 > I wonder ... what would happen when a LARGE packet has been fragmented = by > the sending side, then re-assembled on a Linux router? interesting >=20 > I'm thinking this could be happening, this way the packets you get are = 1500 > bytes, but being re-assembled into something massive ... which overflow= s the > small buffer used for reading from ipq. >=20 > Changing IPQ_BUFSIZE will tell us if this is true >=20 >=20 > Ravi Patwari wrote: >> How do I check this. I have not made any specific change anywhere that= =20 >> I know of. >> >> -Ravi >> >> -----Original Message----- >> From: Nigel Kukard [mailto:nk...@lb...] >> Sent: Tuesday, July 25, 2006 8:23 PM >> To: ra...@sw... >> Subject: Re: [bwm-tools-tech] Configuration >> >> Is it possible your packets are larger than 1500 bytes? >> >> -Nigel >> >> >> Ravi Patwari wrote: >>> Hi Nigel, >>> >>> Please help me on this problem with bwmd as it does not seem to be=20 >>> handling packets from the QUEUE correctly. >>> >>> By the way I am using CentOS, which is redhat enterprise linux.=20 >>> >>> Regards >>> Ravi >>> >>> -----Original Message----- >>> From: Nigel Kukard [mailto:nk...@lb...] >>> Sent: Monday, July 24, 2006 3:05 PM >>> To: ra...@sw...; Bandwidth Management Tools General &=20 >>> Technical Discussions >>> Subject: Re: [bwm-tools-tech] Configuration >>> >>> >>>> =20 >>>> On running bwmd, I immediately get the following: >>>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D >>>> BWM Daemon v0.2.3 - Copyright (c) 2003-2006 Linux Based Systems=20 >>>> Design >>>> =20 >>>> BWMD: Loaded 20 flows and 18 queues >>>> BWMD: Found 1 modules to load >>>> Loading ip_queue...done >>>> IPQ runner started... >>>> Flow runner started... >>>> Stat thread started... >>>> Report runner started... >>>> Failed to get packet from IPQ: Received message truncated >>>> passer: Received message truncated >>>> >>>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D >>>> =20 >>> Can you try the latest development snapshot please. >>> >>> -Nigel >>> >>> >>> >> >> >=20 >=20 >=20 |
|
From: Nigel K. <nk...@lb...> - 2006-07-28 20:13:28
Attachments:
signature.asc
|
Hi Ravi, > Now, almost 24 hours after the IPQ_BUFSIZE change, all is well. This is= FYI. > =20 Great, I'll work on bringing out a fix in the next snapshot. > In the mailing list I see that bwmd can log direct to rrd files, how? A= lso I > had compiled bwm_tools as under: > > ./configure --with-rrdtool2 --disable-rrdcgi > > As in the mailing list you are saying that live stats can be got using > rrdcgi. > > Is there some documentation on this please and examples. Check out the doc directory, you can make pdf or make html =20 to generate documentation. You're looking for the report-format option, setting this to rrd can generate rrd data. You will need to create the rrd file first though, and specify it using report-filename. Bwmd will log 4 values to the rrd every report-timeout, bytes, packets, bursted, dropped respectively. Check this script out .... http://www.linuxrulz.org/nkukard/scripts/stats.cgi .... thats a starting point to write your own cgi script which generates funky rrdtool graphs = :) Let me know if you come right, I'll work on better documenting the reporting directly to rrd the first chance I get. This should serve as information for anyone who takes the time to look through the mailing list archives ;) Regards Nigel |
|
From: Ravi P. <ra...@sw...> - 2006-07-29 12:11:12
|
Hi Nigel I see from the rrd created by bwm_graph using the size_bit option, it can measure or record a max of 1Mbit only. Please clarify where to correct this from. Also I am unable to check out your script below as the file does not seem to be there. Please advise. Regards Ravi -----Original Message----- From: bwm...@li... [mailto:bwm...@li...] On Behalf Of Nigel Kukard Sent: Wednesday, July 26, 2006 9:34 PM To: Bandwidth Management Tools General & Technical Discussions Subject: Re: [bwm-tools-tech] Configuration Hi Ravi, > Now, almost 24 hours after the IPQ_BUFSIZE change, all is well. This is FYI. > Great, I'll work on bringing out a fix in the next snapshot. > In the mailing list I see that bwmd can log direct to rrd files, how? > Also I had compiled bwm_tools as under: > > ./configure --with-rrdtool2 --disable-rrdcgi > > As in the mailing list you are saying that live stats can be got using > rrdcgi. > > Is there some documentation on this please and examples. Check out the doc directory, you can make pdf or make html to generate documentation. You're looking for the report-format option, setting this to rrd can generate rrd data. You will need to create the rrd file first though, and specify it using report-filename. Bwmd will log 4 values to the rrd every report-timeout, bytes, packets, bursted, dropped respectively. Check this script out .... http://www.linuxrulz.org/nkukard/scripts/stats.cgi .... thats a starting point to write your own cgi script which generates funky rrdtool graphs :) Let me know if you come right, I'll work on better documenting the reporting directly to rrd the first chance I get. This should serve as information for anyone who takes the time to look through the mailing list archives ;) Regards Nigel |
|
From: Ravi P. <ra...@sw...> - 2006-07-31 12:55:17
|
Hi Nigel, I am still facing the following issues: (a) Though bwmd is running and updating the respective .dat files in /var/bwm_tools, the rrds created from these .dat files are not having any entries beyond midnight of 30 jul 2006. Any particular reason? (b) The graphs created by using size_bit counter do not go over 1Mbit. Where do I change this code so that the rrd files generated can record this properly. (c) No scripts available in the link below. Please advise. Regards Ravi -----Original Message----- From: bwm...@li... [mailto:bwm...@li...] On Behalf Of Nigel Kukard Sent: Wednesday, July 26, 2006 9:34 PM To: Bandwidth Management Tools General & Technical Discussions Subject: Re: [bwm-tools-tech] Configuration Hi Ravi, > Now, almost 24 hours after the IPQ_BUFSIZE change, all is well. This is FYI. > Great, I'll work on bringing out a fix in the next snapshot. > In the mailing list I see that bwmd can log direct to rrd files, how? > Also I had compiled bwm_tools as under: > > ./configure --with-rrdtool2 --disable-rrdcgi > > As in the mailing list you are saying that live stats can be got using > rrdcgi. > > Is there some documentation on this please and examples. Check out the doc directory, you can make pdf or make html to generate documentation. You're looking for the report-format option, setting this to rrd can generate rrd data. You will need to create the rrd file first though, and specify it using report-filename. Bwmd will log 4 values to the rrd every report-timeout, bytes, packets, bursted, dropped respectively. Check this script out .... http://www.linuxrulz.org/nkukard/scripts/stats.cgi .... thats a starting point to write your own cgi script which generates funky rrdtool graphs :) Let me know if you come right, I'll work on better documenting the reporting directly to rrd the first chance I get. This should serve as information for anyone who takes the time to look through the mailing list archives ;) Regards Nigel |
|
From: Nigel K. <nk...@lb...> - 2006-07-31 12:59:46
Attachments:
signature.asc
|
Hi Ravi, > (a) Though bwmd is running and updating the respective .dat files in > /var/bwm_tools, the rrds created from these .dat files are not having a= ny > entries beyond midnight of 30 jul 2006. Any particular reason? > =20 Can you paste the command(s) you're using to generate the rrd? Are you using native or rrd format? > (b) The graphs created by using size_bit counter do not go over 1Mbit. = Where > do I change this code so that the rrd files generated can record this > properly. > =20 Hrmmm ... can you bzip2 one of your .dat files and send it to me, I'll investigate. > (c) No scripts available in the link below. Please advise. > =20 use ... wget http://www.linuxrulz.org/nkukard/scripts/stats.cgi It won't show up in a browser. Regards -Nigel |
|
From: Ravi P. <ra...@sw...> - 2006-07-28 06:55:27
|
Almost 5 hours and no problems so far, neither on RAM or CPU as well. If it can saturate a gigabit card, then its really good in fact better than commercial products I know. Fantastic Job Nigel and thanks to all who have helped in developing this product. What do you mean renicing bwm?? Regards Ravi -----Original Message----- From: Nigel Kukard [mailto:nk...@lb...] Sent: Tuesday, July 25, 2006 9:55 PM To: ra...@sw... Cc: bwm...@li... Subject: Re: [bwm-tools-tech] Configuration > Ok changed IPQ_BUFSIZE to 16384 and recompiled and it seems to be > working for the last 5 minutes without any errors. Will keep you posted. Cool .... only drawback is bwm will now eat ram like its going out of fashion ... not tooo bad though, I'll try address the problem in the next development release. > > Please advise if you want me to do anything else on the box. > > CPU usage is also around 1-3% only. Great ... > > Thanks very much for your help. > > What are the limitations of bwm? I will be playing around with the > graphing utilities and will get back to you in case of any problems. Well ... I've tried it out on a switched Gbit network and managed to fully saturate the network cards ... on a celeron D 2.8 it pulled about 30% CPU. I would also recommend you maybe increase your ip_queue size to 32768 or something, just incase something else munches CPU and bwm is unable to keep up .... I'm also looking at renicing bwm to give it high priority aswell. -Nigel > > Thanks again. > > Regards > Ravi > > -----Original Message----- > From: Nigel Kukard [mailto:nk...@lb...] > Sent: Tuesday, July 25, 2006 8:29 PM > To: ra...@sw... > Subject: Re: [bwm-tools-tech] Configuration > > I wonder ... what would happen when a LARGE packet has been fragmented > by the sending side, then re-assembled on a Linux router? interesting > > I'm thinking this could be happening, this way the packets you get are > 1500 bytes, but being re-assembled into something massive ... which > overflows the small buffer used for reading from ipq. > > Changing IPQ_BUFSIZE will tell us if this is true > > > Ravi Patwari wrote: >> How do I check this. I have not made any specific change anywhere >> that I know of. >> >> -Ravi >> >> -----Original Message----- >> From: Nigel Kukard [mailto:nk...@lb...] >> Sent: Tuesday, July 25, 2006 8:23 PM >> To: ra...@sw... >> Subject: Re: [bwm-tools-tech] Configuration >> >> Is it possible your packets are larger than 1500 bytes? >> >> -Nigel >> >> >> Ravi Patwari wrote: >>> Hi Nigel, >>> >>> Please help me on this problem with bwmd as it does not seem to be >>> handling packets from the QUEUE correctly. >>> >>> By the way I am using CentOS, which is redhat enterprise linux. >>> >>> Regards >>> Ravi >>> >>> -----Original Message----- >>> From: Nigel Kukard [mailto:nk...@lb...] >>> Sent: Monday, July 24, 2006 3:05 PM >>> To: ra...@sw...; Bandwidth Management Tools General & >>> Technical Discussions >>> Subject: Re: [bwm-tools-tech] Configuration >>> >>> >>>> >>>> On running bwmd, I immediately get the following: >>>> ================================= >>>> BWM Daemon v0.2.3 - Copyright (c) 2003-2006 Linux Based Systems >>>> Design >>>> >>>> BWMD: Loaded 20 flows and 18 queues >>>> BWMD: Found 1 modules to load >>>> Loading ip_queue...done >>>> IPQ runner started... >>>> Flow runner started... >>>> Stat thread started... >>>> Report runner started... >>>> Failed to get packet from IPQ: Received message truncated >>>> passer: Received message truncated >>>> >>>> ========================= >>>> >>> Can you try the latest development snapshot please. >>> >>> -Nigel >>> >>> >>> >> >> > > > |
|
From: Nigel K. <nk...@lb...> - 2006-07-28 14:44:42
Attachments:
signature.asc
|
Hi, > Almost 5 hours and no problems so far, neither on RAM or CPU as well. > =20 Great. > If it can saturate a gigabit card, then its really good in fact better = than > commercial products I know. :) > What do you mean renicing bwm?? > =20 Giving it a higher scheduling priority, normally user-initiated apps will run with priority 0. With -20 being highest and 20 being lowest. Re-nicing to say -5 on the threads responsible for grabbing and delivering packets would give it higher priority than apps being run on the box. Regards Nigel |
×
Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.
Thanks for helping keep SourceForge clean.
X