- NANOG - lists.nanog.org

Re: questions about DVFS in saving energy
by William Pitcock 14 May '09

14 May '09

Xen handles the AMD HE CPUs just fine here. What sort of breakage are you experiencing? William ------Original Message------ From: Tomas L. Byrnes To: Kai Chen To: nanog(a)merit.edu Subject: RE: questions about DVFS in saving energy Sent: May 13, 2009 2:31 PM -----Original Message----- From: Kai Chen [mailto:kch670@eecs.northwestern.edu] Sent: Wednesday, May 13, 2009 12:25 PM To: nanog(a)merit.edu Subject: questions about DVFS in saving energy Hi, could anyone here have some idea of the following questions about Dynamic Voltage/Frequency Scaling techniques used for energy efficiency, or please give a pointer that I can trace, 1) how many servers in the market support this technique? 2) how many voltages/frequencies can the servers support? 3) What's the transition time and cost (power) between these voltages/frequencies? Thanks, -Kai ________________________________________________________________________ ____________________________________ My experience with the AMD HE CPUs has been that the scaling breaks Win2K3, and any virtualized environments. -- William Pitcock SystemInPlace - Simple Hosting Solutions 1-866-519-6149

3 3

RE: delays to google
by Ben Matthew 14 May '09

14 May '09

Yes me!! No other bugger seems to have noticed until now though. Getting similar traces to you; then it just sorts itself out after 5-10 minutes. I did think it was an issue with my LINX peering. Clearly not (from your trace). Queue the irritated: why don't you just email noc@google emails. Love & kisses, Ben Absolute Radio (AS34763) -----Original Message----- From: Steve Williams [mailto:williams@csr.utexas.edu] Sent: 14 May 2009 16:49 To: nanog(a)merit.edu Subject: delays to google am seeing significant delays in getting to google. anyone else seeing this? $ traceroute www.google.com traceroute: Warning: www.google.com has multiple addresses; using 74.125.53.147 traceroute to www.l.google.com (74.125.53.147), 30 hops max, 40 byte packets 1 cisco-190 (129.116.190.250) 0.430 ms 0.350 ms 0.353 ms 2 ser10-v758.gw.utexas.edu (128.83.10.29) 1.138 ms 1.099 ms 1.057 ms 3 ser2-gi1-9.gw.utexas.edu (128.83.10.2) 10.475 ms 1.174 ms 1.584 ms 4 aust-utnoc-core-ge-6-0-0-0.tx-bb.net (192.12.10.1) 1.215 ms 1.209 ms 1.134 ms 5 te2-1--570.tr01-lsanca01.transitrail.net (137.164.131.221) 40.649 ms 40.699 ms 40.678 ms 6 * * * 7 * * * 8 * * * 9 * * * 10 * * * 11 72.14.232.10 (72.14.232.10) 261.262 ms * * 12 * * pw-in-f147.google.com (74.125.53.147) 251.867 ms -- ''' (O O) ,-------------- oOO-(_)-OOo -------------, | Stephen Williams | | Manager of Computer Services | | Center for Space Research | | University of Texas at Austin | | 3925 W. Braker Ln., Suite 200 | | Austin, TX 78759-5321 | | 512.471.7235 512.471.3570 (fax) | | williams(a)csr.utexas.edu | |____________________ Oooo ______________| oooO ( ) ( ) ) / \ ( (_/ \_) ________________________________________________ DISCLAIMER This e-mail message, including any attachments, is intended solely for the use of the addressee and may contain confidential information. If it is not intended for you, please inform the sender and delete the e-mail and any attachments immediately. Any review, retransmission, disclosure, copying or modification of it is strictly forbidden. Please be advised that the views and opinions expressed in this e-mail may not reflect the views and opinions of TIML Radio Limited or any of its parent and subsidiary companies. Whilst we take reasonable precautions to ensure that our emails are free from viruses, we cannot be responsible for any viruses transmitted with this e-mail and recommend that you subject any incoming e-mail to your own virus checking procedures. Use of this or any other e-mail facility signifies consent to any interception we might lawfully carry out to prevent abuse of these facilities. ________________________________________________ TIML Radio Limited (trading as Absolute Radio) Registered office: One Golden Square, London. W1F 9DJ Registered in England No 02674136 VAT No 927 2572 11

1 0

Joel M. Wheeler is out of the office.
by JMWheeler＠dstsystems.com 14 May '09

14 May '09

I will be out of the office starting 05/14/2009 and will not return until 05/15/2009. I will be out of the office on Thursday 5/14. I will repsond to your e-mail when I return on Friday 5/15. ----------------------------------------- Please consider the environment before printing this email and any attachments. This e-mail and any attachments are intended only for the individual or company to which it is addressed and may contain information which is privileged, confidential and prohibited from disclosure or unauthorized use under applicable law. If you are not the intended recipient of this e-mail, you are hereby notified that any use, dissemination, or copying of this e-mail or the information contained in this e-mail is strictly prohibited by the sender. If you have received this transmission in error, please return the material received to the sender and delete all copies from your system.

1 0

how many BGP routers, how many ASes
by Irfan Zakiuddin 13 May '09

13 May '09

Hi all, I have scouted around for this information, but not get very far. I'm hoping someone will have answers at hand. What I want to know is roughly how many : 1. ASes there are in the world today? 2. BGP routers there are, for intra-domain as well as inter-domain routing, in total in the world? 3. BGP routers do the largest ASes have? Really interesting would then be to say either how fast the above numbers are growing, or to give estimates for what the answers to 1-3 will be in 5 years time. An Internet source that provides the above information would be most useful - though I can't seem to find it with google. I'd be grateful for answer to be sent to me directly, whether you also post to NANOG is up to you. thanks in advance. irfan

9 8

questions about DVFS in saving energy
by Kai Chen 13 May '09

13 May '09

Hi, could anyone here have some idea of the following questions about Dynamic Voltage/Frequency Scaling techniques used for energy efficiency, or please give a pointer that I can trace, 1) how many servers in the market support this technique? 2) how many voltages/frequencies can the servers support? 3) What’s the transition time and cost (power) between these voltages/frequencies? Thanks, -Kai

2 1

Network Performance Monitoring/Route Optimization products
by Drew Weaver 13 May '09

13 May '09

Hi there, I am trying to get some opinions on what people are using these days for network performance monitoring software/(appliances?) which can give a sense of what performance is like for the folks actually using the network. Does anyone have any advice on this matter and have you found that these tools are really useful in pinpointing trouble spots before they become major issues? Also, does anyone know of any companies who have new and exciting products which compete with the Internap FCP/Routescience(Avaya) box in the Routing Optimization space? I haven't really been able to find anything except for those two, and Avaya is clearly moving in a more enterprise direction (rather than ISP/service provider) with the CNA. Off-list is fine if you like. Thanks, -Drew

2 2

Multilink PPPoE Scalability Issue
by Sarpreet 12 May '09

12 May '09

Please help :) The network topology is: ADSL CPE (Cisco 2800) +===[PPPoE]===+ LAC (Telco's equipment) +===[L2TP]===+ LNS (Cisco 7513) The setup is for aggregating multiple PPPoE DSL lines with PPP. Using the Cisco 7513 as the LNS, the setup works up to 15 MLPPP bundles and with Cisco 7200-NPE400 only works up to 5 MLPPP bundles. After that, additional MLPPP bundle attempting to connect won't be able to complete IPCP phrase--the L2TP tunnels are created, each individual PPP link members are up, and the MLPPP bundle is created, just cannot finish the IP "handshake" part of the IPCP phrase. In fact, even a normal PPP (without Multilink) session won't be able to complete the IPCP phrase as long as there are 15 active working MLPPP bundle is on. I have search through Cisco's website to see if there is any documented limitation/restriction on the number of bundles the 7513 can support. The closest thing I can find is an reference to a 7500 w/ VIP4-80 can only support a limited number of T1 MLPPP bundles ( http://www.cisco.com/en/US/docs/ios/12_0t/12_0t3/feature/guide/multippp.htm… ). Cisco 7513 spec: Cisco IOS Software, RSP Software (RSP-JSV-M), Version 12.4(21), RELEASE SOFTWARE (fc1) Cisco RSP8 (R7000) processor with 262144K/8216K bytes of memory. R7000 CPU at 250MHz, Implementation 39, Rev 2.1, 256KB L2, 2048KB L3 Cache Last reset from power-on Chassis Interface. 1 FEIP2 controller (2 FastEthernet). 2 FastEthernet interfaces 2043K bytes of NVRAM. 62720K bytes of ATA PCMCIA card at slot 0 (Sector size 512 bytes). 16384K bytes of Flash internal SIMM (Sector size 256K). Cisc 2800 spec: Cisco IOS Software, 2800 Software (C2800NM-ADVIPSERVICESK9-M), Version 12.4(15)T3, RELEASE SOFTWARE (fc1) Cisco 2811 (revision 53.51) with 247808K/14336K bytes of memory. Processor board ID FTX0945A4WJ 2 FastEthernet interfaces 3 ATM interfaces 1 Virtual Private Network (VPN) Module DRAM configuration is 64 bits wide with parity enabled. 239K bytes of non-volatile configuration memory. 62720K bytes of ATA CompactFlash (Read/Write) ----------- Relevant CPE config: ----------------- interface ATM0/0/0 no ip address no atm ilmi-keepalive dsl operating-mode auto pvc 0/33 tx-ring-limit 3 vc-hold-queue 80 pppoe-client dial-pool-number 1 ! ! interface ATM0/1/0 no ip address no atm ilmi-keepalive dsl operating-mode auto pvc 0/33 tx-ring-limit 3 vc-hold-queue 80 pppoe-client dial-pool-number 1 ! ! interface Dialer1 mtu 1486 ip address x.x.x.1 255.255.255.0 encapsulation ppp dialer pool 1 no keepalive no fair-queue no cdp enable ppp chap hostname abc(a)smarttadsl.com ppp chap password highlysecretive ppp pap sent-username vaamadsl(a)smarttadsl.com password highlysecretive ppp link reorders ppp multilink ppp multilink fragment disable ! ip route 0.0.0.0 0.0.0.0 Dialer1 ----------- Relevant LNS config: ----------------- aaa authentication ppp default group radius aaa accounting network default start-stop group radius vpdn enable ! vpdn-group 1 ! Default L2TP VPDN group accept-dialin protocol l2tp virtual-template 1 lcp renegotiation always l2tp tunnel password faketunnelpass ip mtu adjust interface FastEthernet8/1/0 description Facing-LAC ip address y.y.y.5 255.255.255.252 ip tcp adjust-mss 1446 full-duplex fair-queue ! interface Virtual-Template1 ip address x.x.x.254 255.255.255.0 no peer default ip address no keepalive ppp mtu adaptive ppp authentication pap ppp link reorders ppp multilink ppp multilink fragment disable ! Sarpreet Basi Knowledge Computers sar(a)knowledgecomputers.net

1 0

Re: two interfaces one subnet
by William Pitcock 12 May '09

12 May '09

Completely off topic but, does this subject make anyone else immediately think of 2girls1cup? I blame the internets for my making this correlation... ------Original Message------ From: Martin Hannigan To: Patrick W. Gilmore Cc: NANOG list Subject: Re: two interfaces one subnet Sent: May 12, 2009 11:06 AM On Tue, May 12, 2009 at 12:12 AM, Patrick W. Gilmore <patrick(a)ianai.net>wrote: > On May 11, 2009, at 11:43 PM, Ben Scott wrote: > >> On Mon, May 11, 2009 at 11:01 PM, Patrick W. Gilmore <patrick(a)ianai.net> >> wrote: >> > > Do you even read your own posts? Specifically: >>> >>> On May 11, 2009, at 5:40 PM, Ben Scott wrote: >>> >>> Either way, if >>>> the packet *from* X was addressed *to* B but the response comes back >>>> from *A*, then host X is going to drop the packet as >>>> invalid/irrelevant/etc. >>>> >>> >>> The receiving host X does not care (or even know) if A and B are in the >>> same >>> prefix. >>> >> >> Look again. A and B are *IP addresses*, not hosts. >> > > Sometimes people agree with me, sometimes they don't, and sometimes I agree > with them. But I've yet to have someone claim to be arguing against me > while proving my point. > > Anyone else want to unconfused Ben? I obviously cannot. Really nothing clever about this at all in application or practicality. host> cat /etc/services | grep nntp nntp 119/tcp readnews untp # USENET News Transfer Protocol host1> cat /etc/hosts | grep news 127.0.0.1 localhost 192.168.0.100 clue-store 192.168.0.100 news-out 192.168.0.101 news-in If this didn't work, you'd suppose that virtual machines and IP aliasing wouldn't work either. Unless routes facing the world on the device are "tweaked", this should work fine and be reliable (if implemented cluefully). Am I not getting it? Best, -M< -- Martin Hannigan martin(a)theicelandguy.com p: +16178216079 Power, Network, and Costs Consulting for Iceland Datacenters and Occupants -- William Pitcock SystemInPlace - Simple Hosting Solutions 1-866-519-6149

1 0

10-GigE for servers
by Jason Shoemaker 12 May '09

12 May '09

My company is looking for ways to improve throughput for data transfers between individual servers. We’re exploring the creation of Etherchannels using multiple server NICs, but Etherchannel seems to have the limitation of not supporting per-packet load-balancing, therefore limiting traffic between two individual hosts to 1 Gig. In most of my research, I’ve seen 10-GigE used for traffic aggregation and for the “unified fabric” solution that Cisco and others are pushing. I’m interested in knowing if any of you have attempted to implement 10-GigE at the host level to improve network throughput between individual servers and what your experience was in doing so. Thanks in advance, Jason

9 8

Can Interdomain routing[BGP] self recover from prefix hijack?
by Akmal Shahbaz 12 May '09

12 May '09

HiSolutions like BGPmon.net,Cyclops,etc are doing a very good job of alerting about the prefix hijack/configuration erros/experiments gonig on/etc.But i would like to ask "Alerting the victim is the best we can do after detecting such incidents" or what else we can do?What do you think about "BGP ability to Self recover form prefix hijacks or anomalies?" Is it possible?How?What do you think about "Self healing as the property of Internet?"Thank you.Akmal KhanMS-PhD StudentMMLab(a)SNU.Kr --- On Tue, 5/12/09, nanog-request(a)nanog.org <nanog-request(a)nanog.org> wrote: From: nanog-request(a)nanog.org <nanog-request(a)nanog.org> Subject: NANOG Digest, Vol 16, Issue 43 To: nanog(a)nanog.org Date: Tuesday, May 12, 2009, 1:04 AM Send NANOG mailing list submissions to nanog(a)nanog.org To subscribe or unsubscribe via the World Wide Web, visit http://mailman.nanog.org/mailman/listinfo/nanog or, via email, send a message with subject or body 'help' to nanog-request(a)nanog.org You can reach the person managing the list at nanog-owner(a)nanog.org When replying, please edit your Subject line so it is more specific than "Re: Contents of NANOG digest..." Today's Topics: 1. Re: two interfaces one subnet (David Devereaux-Weber) 2. Re: two interfaces one subnet (Nathan Ward) 3. Re: two interfaces one subnet (Arnold Nipper) 4. Re: two interfaces one subnet (Patrick W. Gilmore) 5. Re: two interfaces one subnet (Patrick W. Gilmore) 6. RE: two interfaces one subnet (Holmes,David A) 7. Re: two interfaces one subnet (Arnold Nipper) 8. Re: two interfaces one subnet (Patrick W. Gilmore) 9. Re: two interfaces one subnet (Chris Adams) 10. Re: two interfaces one subnet (Kevin Oberman) 11. Re: two interfaces one subnet (Ben Scott) ---------------------------------------------------------------------- Message: 1 Date: Mon, 11 May 2009 17:08:45 -0500 From: David Devereaux-Weber <ddevereauxweber(a)gmail.com> Subject: Re: two interfaces one subnet To: Hector Herrera <hectorherrera(a)gmail.com> Cc: nanog(a)nanog.org Message-ID: <f2675b350905111508t11d097afrb68ecb09d3798025(a)mail.gmail.com> Content-Type: text/plain; charset=ISO-8859-1 In my case, each Ethernet interface has its own unique MAC address. Dave On Mon, May 11, 2009 at 4:28 PM, Hector Herrera <hectorherrera(a)gmail.com>wrote: > On Mon, May 11, 2009 at 2:22 PM, David Devereaux-Weber > <ddevereauxweber(a)gmail.com> wrote: > > Chris, > > > > I work with iHDTV <http://ihdtv.org>, a project that sends uncompressed > high > > definition television (1.5 Gbps) as UDP over two 1 Gbps interfaces. If > both > > interfaces are on the same subnet, the OS sees the same router (gateway) > > address on both interfaces, and the results are sub-optimal ... around > 50% > > packet loss. > > packet loss is probably due to the network switch having to re-learn > the location of the MAC address constantly as it sees packets on two > or more ports with the same MAC address (think STP loops). > > If your network stack and network device (switch) supports LACP, then > you can have multiple connections between a host and a network device. > That is a very easy way to increase capacity and add redundancy. > > That is how all of our VMWare ESX 3.5i servers are connected. > > Hector > ------------------------------ Message: 2 Date: Tue, 12 May 2009 10:08:49 +1200 From: Nathan Ward <nanog(a)daork.net> Subject: Re: two interfaces one subnet To: nanog list <nanog(a)nanog.org> Message-ID: <24F5463D-C5B0-46BD-AB6A-1C376BE742EF(a)daork.net> Content-Type: text/plain; charset=US-ASCII; format=flowed; delsp=yes On 12/05/2009, at 9:00 AM, Charles Wyble wrote: > What does two interfaces in one subnet mean? > > Two NICs? Or virtual interfaces? Also, what does one subnet mean? A. Using the same IP prefix on two different networks (ie. ethernet broadcast domains) with an interface in to each, or B. running two interfaces in to the same network (ie. ethernet broadcast domain). In the case of A, are you re-using numbers on each side? In the case of B, are you wanting both interfaces to have the same number(s)? -- Nathan Ward ------------------------------ Message: 3 Date: Tue, 12 May 2009 00:13:19 +0200 From: Arnold Nipper <arnold(a)nipper.de> Subject: Re: two interfaces one subnet To: "Patrick W. Gilmore" <patrick(a)ianai.net> Cc: NANOG list <nanog(a)nanog.org> Message-ID: <4A08A2FF.4040306(a)nipper.de> Content-Type: text/plain; charset="iso-8859-1" On 11.05.2009 23:47 Patrick W. Gilmore wrote > On May 11, 2009, at 5:19 PM, Alex H. Ryu wrote: > >> It may be allowed from host-level, but from router equipment, I don't >> think it was allowed at all. > > Ever used HSRP / VRRP? Two interfaces in the same subnet. Works > fine. In fact, most people think it works _better_ than one interface > in the same subnet. > I guess you are mixing interfaces with IPs now. Don't you? Arnold -- Arnold Nipper / nIPper consulting, Sandhausen, Germany email: arnold(a)nipper.de phone: +49 6224 9259 299 mobile: +49 172 2650958 fax: +49 6224 9259 333

1 0