RE: ATM Bandwith [7:71937]
=?iso-8859-1?q?Gerard=20Torin?= wrote: Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. Bandwidth means capacity. It is a given. The amount of bandwidth you have is dictated by your provider and the type of interface you are using. It is not measured. It doesn't change (unless you have some technology that uses dynamic bandwidth allocation, such as multilink PPP). What you seem to be doing is measuring throughput. Throughput is measured. It's the amount of data per timeframe that can be sent. Because they have the same unit of measurement (bits per second or something similiar) people think bandwidth and throughput mean the same thing. They don't. Just want to encourage people to use the terms correctly! :-) Now, throughput can measure numerous different things. If you had a tool that could send raw, unframed bits as fast as the interface allows, throughput could equal bandwidth, assuming the link is not used by anything but your testing tool. Since such tools aren't very common, and, of more importance, don't resemble real-world applications, that's not how throughput is really measured. What you really care about is the user's experience. So you care about application-layer throughput. Some tools let you measure the amount of user data that is sent per unit of time. This refers to the application-layer payload. It leaves out overhead caused by headers at the data-link, network, transport, and application layer. Or you can measure throughput using a tool that does count data-link layer overhead, or network, or whatever. If you don't know what your tool is measuring, find out. Otherwise your results are meaningless. Throughput, depending on what layer you are measuring, can be affected by numerous factors: * packet header overhead (and ATM cell overhead) * errors, resulting in retransmissions and dropped frames * dropped frames at internetworking devices due to buffer overflows * media contention on shared links * protocol behavior, including the need to find a resource, set up a connection, ack data, etc. * RAM access speed at end systems and internetworking devices * hard drive access speed at end systems * processing required at end systems and internetworking devices * software inefficiencies And about a zillion other things, depending on what you are actually measuring, which is not bandwidht, but is throughput at some layer. :-) ___ Priscilla Oppenheimer www.priscilla.com I thanks any comment. - Yahoo! Messenger Nueva versioacute;n: Super Webcam, voz, caritas animadas, y maacute;s #161;Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71999t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
RE: ATM Bandwith [7:71937]
=?iso-8859-1?q?Gerard=20Torin?= wrote: Hi Dom, we did test with TFY aplication, generating a burst traffic of 3000 bytes UDP. Where is the testing being done? Is it through a path that actually handles a 3000-byte packet without IP fragmentation? ATM might default to a high MTU, but if you're starting on Ethernet, then you can't use such a large MTU. So that means that you're doing IP fragmentation. That takes time and causes even more overhead from headers. UDP has an 8-byte header. IP has a 20 byte header. Ethernet supports an MTU of 1500 bytes. So, first figure out what your tool means by 3000-byte packet. Does it count headers? But probaby you want to test with 1472 at most, assuming you're starting on an Ethernet link. If you're starting on ATM, find out the MTU for the ATM interface. So, add to my list of things that affect throughput (not bandwidth): IP fragmentation and reassembly. Thanks, Priscilla This aplication stressed the link, but I don`t undestard why not reach the maximun bandwith permited: 34Mbps. What do you think about this test? Is right? Dom wrote: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gerard Torin Sent: 05 July 2003 19:06 To: [EMAIL PROTECTED] Subject: ATM Bandwith [7:71937] Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. Please supply more details. How did you test and with what size packets? Cell tax (the overhead of breaking your data down in 53byte chunks) might account for hat you are observing. Best regards, Dom Stocqueler SysDom Technologies Visit our website - www.sysdom.org Yahoo! Messenger Nueva versioacute;n: Super Webcam, voz, caritas animadas, y maacute;s #161;Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=72002t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
Re: ATM Bandwith [7:71937]
Hi, ATM technology is based on 53 byte cells. Also ATM has a 5 byte header per cell. So your payloads length can be 48 bytes per ATM cell. with a basic calculation, for an ip traffic on 34Mb ATM link : 48 (payload includes the ip header) / 53 (total bytes can be trasnfered in a cell) equals to 0.90566. That means maximum %90.56 of your ATM link can be ip traffic (including the ip headers) so 34Mb * 0.90566 = 30.7925 Mb can be the ip traffic. and also consider that you have ip headers in that traffic, if you calculate the actual payload , it is lesser than that. hope that helps, Gerard Torin wrote: Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. - Yahoo! Messenger Nueva versioacute;n: Super Webcam, voz, caritas animadas, y maacute;s #161;Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71946t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
Re: ATM Bandwith [7:71937]
Hi Levent, I thanks your explanation. It was very good. Best Regards. Levent Ogut wrote: Hi, ATM technology is based on 53 byte cells. Also ATM has a 5 byte header per cell. So your payloads length can be 48 bytes per ATM cell. with a basic calculation, for an ip traffic on 34Mb ATM link : 48 (payload includes the ip header) / 53 (total bytes can be trasnfered in a cell) equals to 0.90566. That means maximum %90.56 of your ATM link can be ip traffic (including the ip headers) so 34Mb * 0.90566 = 30.7925 Mb can be the ip traffic. and also consider that you have ip headers in that traffic, if you calculate the actual payload , it is lesser than that. hope that helps, Gerard Torin wrote: Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. - Yahoo! Messenger Nueva versisn: Super Webcam, voz, caritas animadas, y mas #161;Gratis! Yahoo! Messenger Nueva versioacute;n: Super Webcam, voz, caritas animadas, y maacute;s #161;Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71954t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
RE: ATM Bandwith [7:71937]
Hi Dom, we did test with TFY aplication, generating a burst traffic of 3000 bytes UDP. This aplication stressed the link, but I don`t undestard why not reach the maximun bandwith permited: 34Mbps. What do you think about this test? Is right? Dom wrote: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gerard Torin Sent: 05 July 2003 19:06 To: [EMAIL PROTECTED] Subject: ATM Bandwith [7:71937] Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. Please supply more details. How did you test and with what size packets? Cell tax (the overhead of breaking your data down in 53byte chunks) might account for hat you are observing. Best regards, Dom Stocqueler SysDom Technologies Visit our website - www.sysdom.org Yahoo! Messenger Nueva versioacute;n: Super Webcam, voz, caritas animadas, y maacute;s #161;Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71953t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
RE: ATM Bandwith [7:71937]
Somebody (I'm sorry I deleted the post), posted after me, and it does look like you are hitting the cell tax problem. With other (including layer 3 overheads) you are not doing to badly Sorry if this is not what you want to hear ;) Best regards, Dom Stocqueler SysDom Technologies Visit our website - www.sysdom.org -Original Message- From: Gerard Torin [mailto:[EMAIL PROTECTED] Sent: 06 July 2003 18:29 To: Dom; [EMAIL PROTECTED] Subject: RE: ATM Bandwith [7:71937] Hi Dom, we did test with TFY aplication, generating a burst traffic of 3000 bytes UDP. This aplication stressed the link, but I don`t undestard why not reach the maximun bandwith permited: 34Mbps. What do you think about this test? Is right? Dom wrote: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gerard Torin Sent: 05 July 2003 19:06 To: [EMAIL PROTECTED] Subject: ATM Bandwith [7:71937] Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. Please supply more details. How did you test and with what size packets? Cell tax (the overhead of breaking your data down in 53byte chunks) might account for hat you are observing. Best regards, Dom Stocqueler SysDom Technologies Visit our website - www.sysdom.org _ Yahoo! Messenger Nueva versisn: Super Webcam, voz, caritas animadas, y mas !Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71955t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
RE: ATM Bandwith [7:71937]
Hi Gerard, ATM as a technology per se, is a high overhead technology. As the basic fact the fixed size cell is of 53 bytes and out of it the Cell Header consumes 5 bytes. So the net payload per cell is actually 48 bytes only, so effectively you are having a close to 10% overhead, and it is not the end, you have to leave some bandwidth on the error detection etc things also, because of which you are never able to use more than a tentative 90% bandwidth on any kind of technology. So if you are getting a burst of 30 Mbps on a E3 link, (I would like to know about the bandwidth consumption tool or parameters used by you) you are not doing bad; for sure. HTH Vikram -Original Message- From: Dom [mailto:[EMAIL PROTECTED] Sent: Sunday, July 06, 2003 11:30 PM To: [EMAIL PROTECTED] Subject: RE: ATM Bandwith [7:71937] Somebody (I'm sorry I deleted the post), posted after me, and it does look like you are hitting the cell tax problem. With other (including layer 3 overheads) you are not doing to badly Sorry if this is not what you want to hear ;) Best regards, Dom Stocqueler SysDom Technologies Visit our website - www.sysdom.org -Original Message- From: Gerard Torin [mailto:[EMAIL PROTECTED] Sent: 06 July 2003 18:29 To: Dom; [EMAIL PROTECTED] Subject: RE: ATM Bandwith [7:71937] Hi Dom, we did test with TFY aplication, generating a burst traffic of 3000 bytes UDP. This aplication stressed the link, but I don`t undestard why not reach the maximun bandwith permited: 34Mbps. What do you think about this test? Is right? Dom wrote: -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gerard Torin Sent: 05 July 2003 19:06 To: [EMAIL PROTECTED] Subject: ATM Bandwith [7:71937] Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. Please supply more details. How did you test and with what size packets? Cell tax (the overhead of breaking your data down in 53byte chunks) might account for hat you are observing. Best regards, Dom Stocqueler SysDom Technologies Visit our website - www.sysdom.org _ Yahoo! Messenger Nueva versisn: Super Webcam, voz, caritas animadas, y mas !Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71969t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
ATM Bandwith [7:71937]
Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. - Yahoo! Messenger Nueva versioacute;n: Super Webcam, voz, caritas animadas, y maacute;s #161;Gratis! Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71937t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
RE: ATM Bandwith [7:71937]
-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Gerard Torin Sent: 05 July 2003 19:06 To: [EMAIL PROTECTED] Subject: ATM Bandwith [7:71937] Hi guys, Anybody know how is built the ATM4S Bandwith?. For example, In ATM`s link of 34Mbps, Is true that 4Mbps is just only header?, I ask that, because actually my company has it. But we don4t reach the maximun bandwith of 34Mbps. Yesterday, we did stress test in the link and just only reach 30Mbps. I thanks any comment. Please supply more details. How did you test and with what size packets? Cell tax (the overhead of breaking your data down in 53byte chunks) might account for hat you are observing. Best regards, Dom Stocqueler SysDom Technologies Visit our website - www.sysdom.org Message Posted at: http://www.groupstudy.com/form/read.php?f=7i=71939t=71937 -- FAQ, list archives, and subscription info: http://www.groupstudy.com/list/cisco.html Report misconduct and Nondisclosure violations to [EMAIL PROTECTED]
