[Soekris] thermal problem general crashes ?
Hi List, sorry first for aswering not in a short time, but for this and the other messages I was asking three other peoples first, from them I know exactly one is using not only one net5501 and only on work!!! Example 1: A Security administartor working in a greater insurance company. Many (20 - 25) net5501 with an GB LAN Port PCI card as snort sensors for Host based IDS (Servers) and Network IDS (Switches) The boxes are still placed in a closed up rack in a climated server room (0 till +2 Celsius) Only one PSU were replaced till today. One CF card must also be changed, but this is not couting, because soekris is not the producer! The other both opinions, I will show up in the next post, to much and to long so I will split the posting. At their website soekris is telling something about for what the boxes are to use: 1. Small net services 2. Small routers / servers / vpn / wlan With low power consuming parts. All parts soekris were producing, I mean all the lan and all vpn cards are using low power and dont overheating the soldered on chips from the cards and the boards. Now perhaps some people (surely like me too) were thinking that the cards we insert in, are also using low power, but the chips are overheating or the chips are heating to much the air inside the case. And in my opinion it dosen´t matter that we opend the case, because if a chip is to hot, he is to hot, point. So in my opinion soekris is selling hardware for they descript it on their homepage. An Intel Pro 1000/GT Desktop adapter as a WAN port many, many people use with their net5501 and they don´t flooding the list with their problem, because they have to find out by themselves what is to hot and what runs smooth on the machine. If I´m informed right their are more then 20.000 sold boards and boxes and I think it must be connected to the hell, that only you got two boxes they are malformed or tuched by this error. And if so, why one of this boxes was running with an uptime till over a year? Most forums I view from time to time or have a look in are filled with thoose messages, but never, I repead, never in direct context with the soekris produced lan and vpn cards, even with other low power, but overheating cards or too many services. At this point also it is not unusual thoose people (also likes me, Alvar Kusmar and many other) are having a look to other producers like MikroTik or PC Engines (Alix). But Soekris is also offering on their homepage also custom made cases made from different materials and there are also from other vendors and traders like www.yawarra.com.au and http://soekris.kd85.com. Alix - solid aluminium cases For smal routers or firewalls amd only at home use please. If an electrical strike hits the building or 19 rack, the aluminium cases will smelt in seconds and spread out, if the rack is not closed with a front door, very hot liquid aliminium. This can harm human beings and other devices. And to prevent the employees and devices from damage is also perhaps a administrative job. To store this aluminium cases in professional network enviroments or infrastructures not to be recommend, and this only in my opinion. - Not able to store a hdd inside - only 256 MB of ram - No pci slot MikroTik - metal plate based cases For professional use or also called productive network systems. Hard and software came from one company under one direction and a under one concept. No overheating problems but also not the range and so many options like the other both above delivering and serving. Those chips that can be going hot, because the machine is hard in use are sorted with an passive heat sink and some of their wlan routers give you the abbility to insert 1 - 5 wlan cards and no thermal problem. - Training for the os is expensive - dont let you use much more hardware - not so many services like other delivers ! - stable and compatible to all supported hardware - prof. support - each system needs a licence that must be paid Soekris inc. - Solid metal plate based cases For all, having fun, playing, testing, home use, office use and professional use. From the day he was soldering the first boards in his living room at home till today the company was growing up and also the boards became more powerful. The company is selling boards, cases, lan and vpn cards and supports much operating systems and many, many other hardware. - for each level of need and use - low power using - spare parts from own production - nice price - more ram like alix - more powerful then the most MikroTik devices So in my opinion only the overheating parts like cards from other vendors are the usual suspects in this game. __ Hinweis von ESET NOD32 Antivirus, Signaturdatenbank-Version 6693 (20111208) __ E-Mail wurde geprüft mit ESET NOD32 Antivirus. http://www.eset.com ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com
Re: [Soekris] vr0 using OpenBSD stops responding.
On Dec 10, 2011, at 7:50 AM, Frank Schuhmann wrote: Because you wrote that the Win XP was not producing the problem, but Win 7 should do it, it is perhaps the TCP window scaling, as declared in the RFC 1323. In some similar other cases it was sometimes fixing the problem (pfsense) and in sometimes also not, but to quick test it out the spended time will to be of value. On the BSD side perhaps you try to turn of the scaling, I´m not an OpenBSD professional but it must be turn out by setting up a shell order likes sysctl -w net.inet.tcp.rfc1323=0 If not or it must be typed in, in other direction it will be super that perhaps an OpenBSD familiar list member would correct this please. RFC1323 affects the end to end TCP connection. Unless there is a proxy running on the 5501, its RFC1323 settings won't change things. But I agree with this, and the previous poster, that a likely cause is Win7 using RFC1323 and other TCP optimizations (e.g. SACK) for more efficient transfers, so the 5501 is working harder. However another thing occurs to me. I wonder how Path MTU is being dealt with in this scenario. I have far too much experience[1] with various tunneling methods (e.g. VPN) that do not correctly support Path MTU Discovery. We ended up with the ugly, but effective, kludge of artificially lowering the MTUs on the server and client network stacks to compensate. And about half the time when we deploy something new, it breaks until we remember to change the default MTU setting. Perhaps these new Windows 7 boxes don't have that applied, so you're getting a lot of fragmenting at the 5501, and possibly reassembly (although often this is left to the receiving host to do). Seems like a long shot as the usual symptoms for us is no bulk traffic, but YMMV. -Jed [1] The painful sort. ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] net5501 crashes ?
On Thu, 08 Dec 2011 19:59:05 + Nix n...@esperi.org.uk wrote: On 7 Dec 2011, Attila Kinali told this: I have two stability issues: The CPU runs at 60°C when the system is idle. SIO Temp:+53.0°C (low = -55.0°C, high = +127.0°C) (crit = +127.0°C) (room temperature: 15C.) Configuration is a bare net5501-700 in the standard case, with a low power 2.5 sata harddisk mounted on top of it. That extra heat would be the HDD, then. They really can spit out heat, low power or not (it seems to be correlated mostly with age, I suspect due to bearing wear). The harddisk is new and low power (iirc 1W standby and 3W running). Toghether with the CPU that's about 10W of power at full throttle. As the system is sold with a 25W power supply, hence i'd expect it to be able to disipate at least 20W, but even 10W is too much... and if you have a look at the case, you see why. When using the CPU to its limit (like by using cpuburn), the temperature will rise to 80°C. I see no increase in temperature *at all* under heavy CPU load. I find this very surprising: 120 wakeups per second (from the timer interrupt and the entropy key daemon) shouldn't be stopping the thing from going to sleep and cooling down, should it? (Not that 53C really worries me.) 120 IRQs/s is nothing. Dont forget that a standard Linux system is configured to 250Hz timer interrupts these days. Systems that need to be responsive are even configured to 1kHz timer interrrupts. And as the interrupt service routine is very small, it's still plenty of time to sleep. In short: Even with 120 IRQ/s your system is still basically idle. Running an HDD without a fan in the mix to give some airflow seems risky to me, no matter the case. Why? It's a low power notebook HD. These are made to be run in enviroments where there is no airflow at all. Just a little bit of conduction trough the housing. This has been tested and reproduced with Linux kernels 2.6.38.x, 2.6.39.1 and 3.0.1 (vanilla, no patches). FWIW, I've been using a Soekris net5501 for two and a half years now (no HDD or wifi). Linux kernels from 2.6.30 up to 3.2rc. No crashes not attributable to user error, not one. It's sufficiently reliable that I just bought a second one in case lightning strikes the first one and cuts me off from the Internet :) That's exactly what i'm hitting at: If you run the bare system, you have no problems. If you choose to include some of the accessories (like HD mount or wifi cards) sold toghether with the net5501 (which suggests that these accessories are supported), you will run into problems. At least i and seemingly others did. Attila Kinali -- The trouble with you, Shev, is you don't say anything until you've saved up a whole truckload of damned heavy brick arguments and then you dump them all out and never look at the bleeding body mangled beneath the heap -- Tirin, The Dispossessed, U. Le Guin ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] thermal problem general crashes ?
On Thu, 8 Dec 2011 14:35:22 +0100 Frank Schuhmann f.schuhm...@t-online.de wrote: At their website soekris is telling something about for what the boxes are to use: 1. Small net services 2. Small routers / servers / vpn / wlan I'm using my net5501 as a router. And as i said, WLAN crashes the machine. So i'm using it in a way that is not expected??? With low power consuming parts. All parts soekris were producing, I mean all the lan and all vpn cards are using low power and dont overheating the soldered on chips from the cards and the boards. Those parts were bought from soekris directly. So i assume they have been tested with the net5501, as they have been sold as accessories for the net5501. Alix - solid aluminium cases For smal routers or firewalls amd only at home use please. If an electrical strike hits the building or 19 rack, the aluminium cases will smelt in seconds and spread out, if the rack is not closed with a front door, very hot liquid aliminium. This can harm human beings and other devices. Err... I'm not sure i understand you correctly... But, if you really have a full lightning strike on your alix/soekris box and have the case melting... then the molten metal is the least of your problems as anyone near the box will be already dead. Beside, that the iron sheet of the soekris box will melt as well. And to prevent the employees and devices from damage is also perhaps a administrative job. No, this is actually a job for the architect and electrician. They have to ensure that no lightning strike can enter the building w/o passing trough some absorbers. Any strike that you get trough the power cable, telephone or network sokets is still high enough to fry your electronics and give you a severe shock. But it shouldn't be able to kill you. Much less to melt any metal case. To store this aluminium cases in professional network enviroments or infrastructures not to be recommend, I dont see any reason why aluminium cases should not be used in professional enviroments. I'd rather say that you mix up something. Attila Kinali -- The trouble with you, Shev, is you don't say anything until you've saved up a whole truckload of damned heavy brick arguments and then you dump them all out and never look at the bleeding body mangled beneath the heap -- Tirin, The Dispossessed, U. Le Guin ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] vr0 using OpenBSD stops responding.
Hi Jed, we have had perhaps not exactly the same problem with two soekris net5501-70 boxes with pfSense installed as OS on them and 4 brand new windows 7 based pc´s, but also like the same symptoms as explained by Brandan. In our case the windows 7 firewall in combination with the turn off TCP (RFC1323) was fixing the problem. The RFC1323 was also more pointed on the 7 MBit throughput. Sure I must say OpenBSD is not pfSense, but it is also a BSD based system and the tryout with a short shell order would not steel so many of his time. Best regards Frank -Original Message- From: soekris-tech-boun...@lists.soekris.com [mailto:soekris-tech-boun...@lists.soekris.com] On Behalf Of Jed Clear Sent: Saturday, December 10, 2011 3:10 PM To: soekris-tech@lists.soekris.com Subject: Re: [Soekris] vr0 using OpenBSD stops responding. RFC1323 affects the end to end TCP connection. Unless there is a proxy running on the 5501, its RFC1323 settings won't change things. But I agree with this, and the previous poster, that a likely cause is Win7 using RFC1323 and other TCP optimizations (e.g. SACK) for more efficient transfers, so the 5501 is working harder. __ Hinweis von ESET NOD32 Antivirus, Signaturdatenbank-Version 6707 (20111213) __ E-Mail wurde geprüft mit ESET NOD32 Antivirus. http://www.eset.com ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] FreeBSD/amd64 on Net6501 working!
* Soren Kristensen so...@soekris.com [2011-12-11 10:00:05]: ACPI is on my long list of things to do, I'll better move it up, the basic ACPI stuff needed is not that complicated. The ACPI Power is really complicated, but I have no plan to support that, as active power management is not something you want or need on a always on platform Would the ACPI Power support also cover the CPU speed/power throttling? Matt -- Phased plasma rifle in a forty-watt range? Hey, just what you see, pal. ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] Mikrotik RouterOS fails to boot on Net6501
Hi Stephen, this news sounds really bad for me, but using a mSATA is perhaps also not the best idea because you will lost the license if this device (the mSATA) crashes or is damaged by whatever. But the mSATA option would be perhaps great purposely as a fast caching option. If you do planning to install the RouterOS on a real hdd in combination with the net6501, please be so friendly and inform me over your results. On or over this list, also if you want to do so, directly to my shown email address. It would be great to hear from you in this case. The OS is a kick ass champion, but the trainings are so hard to pay for, ;( and not so many hardware will be supported as other Linux versions do. Good luck with your installation. Best regards and wishes Frank Schuhmann -Original Message- From: soekris-tech-boun...@lists.soekris.com [mailto:soekris-tech-boun...@lists.soekris.com] On Behalf Of Stephen Patrick Sent: Tuesday, December 13, 2011 10:15 AM To: Soekris-tech@lists.soekris.com Subject: [Soekris] Mikrotik RouterOS fails to boot on Net6501 Dear all, Colleagues are trying to run some tests on a 6501, it's not working with various versions of ROS 4.xx and 5.xx. Anyone got any solutions for this? Using mSata drive, NetInstall won't see the drive. Alternatively, using a USB flash drive it wouldnt boot past the third driver once it loaded. Comments welcome, Best regards Stephen __ Hinweis von ESET NOD32 Antivirus, Signaturdatenbank-Version 6707 (20111213) __ E-Mail wurde gepruft mit ESET NOD32 Antivirus. http://www.eset.com ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] net5501 crashes ?
On 13 Dec 2011, Attila Kinali said: On Thu, 08 Dec 2011 19:59:05 + Nix n...@esperi.org.uk wrote: I see no increase in temperature *at all* under heavy CPU load. I find this very surprising: 120 wakeups per second (from the timer interrupt and the entropy key daemon) shouldn't be stopping the thing from going to sleep and cooling down, should it? (Not that 53C really worries me.) 120 IRQs/s is nothing. Dont forget that a standard Linux system is Sorry, that was confusing phrasing on my part. Heavy CPU load wasn't the base load mentioned there: it was a giant 'git gc': 100% CPU for an hour plus. :) I was surprised that the base load of 120 wakeups/sec was apparently still high enough that the thing wasn't able to get any cooler than it was when running the giant 'git gc'. (Maybe lm-sensors is lying to me, but I'd not expect a badly calibrated sensor on the Soekris, it's not exactly an off-the-shelf white box.) configured to 250Hz timer interrupts these days. Systems that need to be responsive are even configured to 1kHz timer interrrupts. And as the interrupt service routine is very small, it's still plenty of time to sleep. In short: Even with 120 IRQ/s your system is still basically idle. It's idle (long-term load average 0.05), but it's doing a lot of wakeups, even if it's not doing much work in each one. Some CPUs require long enough to go to sleep again that hundreds of wakeups/sec really would raise their temperature: maybe that would explain why it doesn't get any hotter when I run it at 100% for ages. Running an HDD without a fan in the mix to give some airflow seems risky to me, no matter the case. Why? It's a low power notebook HD. These are made to be run in enviroments where there is no airflow at all. Just a little bit of conduction trough the housing. Most notebooks have fans these days, but you're right, I suspect it's the CPU that needs it. I've run several PCs in horrible tower cases with no airflow over the HDD at all, and they never went wrong. I'm just being reflexively paranoid without cause, I guess. This has been tested and reproduced with Linux kernels 2.6.38.x, 2.6.39.1 and 3.0.1 (vanilla, no patches). FWIW, I've been using a Soekris net5501 for two and a half years now (no HDD or wifi). Linux kernels from 2.6.30 up to 3.2rc. No crashes not attributable to user error, not one. It's sufficiently reliable that I just bought a second one in case lightning strikes the first one and cuts me off from the Internet :) That's exactly what i'm hitting at: If you run the bare system, you have no problems. If you choose to include some of the accessories (like HD mount or wifi cards) sold toghether with the net5501 (which suggests that these accessories are supported), you will run into problems. You may be right. I'm probably going to get a lan1741 fairly soon, as my Soekris has no spare Ethernet jacks and the demand on them just keeps going up. We'll see if it retains stability after that. (Hell, given my coordination, we'll see if I can manage to plug the card in without snapping the board in two! :P ) -- NULL (void) ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] FreeBSD/amd64 on Net6501 working!
On 12/13/2011 04:33 AM, Matt Dainty wrote: * Soren Kristensen so...@soekris.com [2011-12-11 10:00:05]: ACPI is on my long list of things to do, I'll better move it up, the basic ACPI stuff needed is not that complicated. The ACPI Power is really complicated, but I have no plan to support that, as active power management is not something you want or need on a always on platform Would the ACPI Power support also cover the CPU speed/power throttling? ACPI can be used to provide CPU P-state throttling, but in the case of Intel CPUs, I think SpeedStep is probably a better/easier way to go. Most OSes support it, as long as they can identify the CPU. On FreeBSD, the eist driver already sees that the CPUs support SpeedStep, but doesn't attach due to not having the CPU in its configuration table. -nick Matt -- n...@desert.net - all messages cryptographically signed signature.asc Description: OpenPGP digital signature ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
Re: [Soekris] net5501 crashes ?
On 2011-12-07 19:49, Attila Kinali wrote: When running an WLAN card atheros AR9220 in my case, the system will crash from time to time when the WLAN card is in use. Under what kind of pressure/how often? I had horrible stability with an ath9k based card in the miniPCI slot under Linux 2.6.32*, but I decided to test it again due to this topic coming up. It has passed 6 days of uptime with no issues now, where it would die within minutes under 2.6.32 and similar usage. This is running Linux 3.1.0-1-486 (stock Debian testing). Back when it was crashing it was really bad crashes too: No output to the serial port, it would just suddenly freeze the entire machine. Regards Dennis Jørgensen *I may have tested it under 2.6.37 aswell. If I did, the result was the same. ___ Soekris-tech mailing list Soekris-tech@lists.soekris.com http://lists.soekris.com/mailman/listinfo/soekris-tech
[Soekris] Soekris 6501-70 / 6501-50 Network Throughput under Debian / OpenBSD
Hello list, Just wanted to share some tests I ran recently. OpenBSD 5.0 i386 was freshly installed and no tuning has been done. Default PF rules activated after install (see attached ruleset) Debian 6.0.3 i386 with i686 kernel was as well installed without any tuning. No firewall (iptables etc.) running - no tuning done Setup: Tests #1-5: 6501-70 (1.41a) --- gb ethernet switch Cisco SG100D-08 --- Imac (OSX Lion) Tests #6-8: 6501-50 (1.41a) --- gb ethernet switch Cisco SG100D-08 --- Imac (OSX Lion) As you can see below, there is not much difference in performances between -70 and -50 whether is it OpenBSD running or Debian. However, the difference between OpenBSD and Debian is quite impressive with a 4x factor. Have you guys managed to reproduce such tests? Is there any way to improve the network throughput under OpenBSD? (Any links / document etc. would be greatly appreciated!) Cheers, Test #1: 6501-70 with Debian 6.0 32bits (see dmesg attached) soekris# iperf -i 1 -t 30 -d -c 192.168.1.1 Client connecting to 192.168.1.1, TCP port 5001 TCP window size: 16.0 KByte (default) [ 3] local 192.168.1.2 port 33855 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 3] 0.0- 1.0 sec 95.2 MBytes798 Mbits/sec [ 3] 1.0- 2.0 sec 96.4 MBytes808 Mbits/sec [ 3] 2.0- 3.0 sec 97.0 MBytes814 Mbits/sec [ 3] 3.0- 4.0 sec 97.2 MBytes816 Mbits/sec [ 3] 4.0- 5.0 sec 96.7 MBytes812 Mbits/sec [ 3] 5.0- 6.0 sec 97.1 MBytes814 Mbits/sec [ 3] 6.0- 7.0 sec 97.3 MBytes816 Mbits/sec [ 3] 7.0- 8.0 sec 96.6 MBytes811 Mbits/sec [ 3] 8.0- 9.0 sec 97.1 MBytes815 Mbits/sec [ 3] 9.0-10.0 sec 93.9 MBytes787 Mbits/sec [ 3] 10.0-11.0 sec 97.2 MBytes815 Mbits/sec [ 3] 11.0-12.0 sec 97.4 MBytes817 Mbits/sec [ 3] 12.0-13.0 sec 97.2 MBytes816 Mbits/sec [ 3] 13.0-14.0 sec 97.4 MBytes817 Mbits/sec [ 3] 14.0-15.0 sec 97.7 MBytes819 Mbits/sec [ 3] 15.0-16.0 sec 97.6 MBytes819 Mbits/sec [ 3] 16.0-17.0 sec 97.5 MBytes818 Mbits/sec [ 3] 17.0-18.0 sec 97.0 MBytes813 Mbits/sec [ 3] 18.0-19.0 sec 97.2 MBytes816 Mbits/sec [ 3] 19.0-20.0 sec 97.7 MBytes820 Mbits/sec [ 3] 20.0-21.0 sec 97.7 MBytes820 Mbits/sec [ 3] 21.0-22.0 sec 97.1 MBytes815 Mbits/sec [ 3] 22.0-23.0 sec 97.1 MBytes814 Mbits/sec [ 3] 23.0-24.0 sec 97.5 MBytes818 Mbits/sec [ 3] 24.0-25.0 sec 97.3 MBytes816 Mbits/sec [ 3] 25.0-26.0 sec 97.3 MBytes816 Mbits/sec [ 3] 26.0-27.0 sec 97.0 MBytes814 Mbits/sec [ 3] 27.0-28.0 sec 96.2 MBytes807 Mbits/sec [ 3] 28.0-29.0 sec 96.8 MBytes812 Mbits/sec [ 3] 29.0-30.0 sec 97.3 MBytes816 Mbits/sec [ 3] 0.0-30.0 sec 2.84 GBytes814 Mbits/sec imac# iperf -s [ 4] local 192.168.1.1 port 5001 connected with 192.168.1.2 port 33855 [ 4] 0.0-30.0 sec 2.84 GBytes 814 Mbits/sec Test #2: 6501-70 with OpenBSD 5.0 i386 GENERIC.MP / PF enabled (see dmesg attached) soekris# iperf -i 1 -t 30 -d -c 192.168.1.1 Client connecting to 192.168.1.1, TCP port 5001 [ 3] local 192.168.1.2 port 19447 connected with 192.168.1.1 port 5001 [ ID] Interval Transfer Bandwidth [ 3] 0.0- 1.0 sec 21.8 MBytes 182 Mbits/sec [ 3] 1.0- 2.0 sec 22.0 MBytes 185 Mbits/sec [ 3] 2.0- 3.0 sec 21.9 MBytes 184 Mbits/sec [ 3] 3.0- 4.0 sec 21.9 MBytes 184 Mbits/sec [ 3] 4.0- 5.0 sec 22.0 MBytes 185 Mbits/sec [ 3] 5.0- 6.0 sec 20.9 MBytes 175 Mbits/sec [ 3] 6.0- 7.0 sec 21.6 MBytes 181 Mbits/sec [ 3] 7.0- 8.0 sec 21.2 MBytes 178 Mbits/sec [ 3] 8.0- 9.0 sec 20.8 MBytes 174 Mbits/sec [ 3] 9.0-10.0 sec 20.8 MBytes 174 Mbits/sec [ 3] 10.0-11.0 sec 20.8 MBytes 174 Mbits/sec [ 3] 11.0-12.0 sec 20.9 MBytes 175 Mbits/sec [ 3] 12.0-13.0 sec 20.6 MBytes 173 Mbits/sec [ 3] 13.0-14.0 sec 20.8 MBytes 174 Mbits/sec [ 3] 14.0-15.0 sec 20.8 MBytes 174 Mbits/sec [ 3] 15.0-16.0 sec 21.4 MBytes 179 Mbits/sec [ 3] 16.0-17.0 sec 20.9 MBytes 175 Mbits/sec [ 3] 17.0-18.0 sec 20.2 MBytes 170 Mbits/sec [ 3] 18.0-19.0 sec 21.0 MBytes 176 Mbits/sec [ 3] 19.0-20.0 sec 21.5 MBytes 180 Mbits/sec [ 3] 20.0-21.0 sec 20.5 MBytes 172 Mbits/sec [ 3] 21.0-22.0 sec 21.1 MBytes 177 Mbits/sec [ 3] 22.0-23.0 sec 21.1 MBytes 177 Mbits/sec [ 3] 23.0-24.0 sec 21.5 MBytes 180 Mbits/sec [ 3] 24.0-25.0 sec 20.6 MBytes 173 Mbits/sec [ 3] 25.0-26.0 sec 21.1 MBytes 177 Mbits/sec [ 3] 26.0-27.0 sec 21.5 MBytes 180 Mbits/sec [ 3] 27.0-28.0 sec 21.1 MBytes 177 Mbits/sec [ 3] 28.0-29.0 sec 21.2 MBytes 178 Mbits/sec [ 3] 29.0-30.0 sec 21.5 MBytes 180 Mbits/sec [ 3] 0.0-30.0 sec 635 MBytes 177 Mbits/sec imac# iperf -s [ 4] local 192.168.1.1 port 5001 connected with 192.168.1.2 port 19447 [ 4] 0.0-30.0 sec