search for: gbit

Hi, I wonder about the performance of a Linux box used as router (I guest I''m not the first :). Althought I know it mainly depends on the hardware, I''m trying to find some references on the topic or comparations with other routing solutions (FreeBSD box used as router, Cisco, etc). For example, http://facweb.cti.depaul.edu/jyu/Publications/Yu-Linux-TSM2004.pdf (althought is

Hello listmates, As some of you may know we have been having a really bad problem with Realtek Semiconductor Co., Ltd. RTL-8169 cards. See here for details: http://forum.nginx.org/read.php?24,140124,140224 So now my question is, what PCI 1 Gbit/s Ethernet adapters should I use under CentOS? If you have had a consistent positive experience with any particular chipset/brand please speak up. Thanks. Boris.

...uot;$0") "$dir/network-bridge" "$@" vifnum=0 netdev=eth0 bridge=xenbr0 "$dir/network-bridge" "$@" vifnum=1 netdev=eth0.100 bridge=xenbr100 "$dir/network-bridge" "$@" vifnum=2 netdev=eth0.200 bridge=xenbr200 If the server has a 1 Gbit network card (e1000, tg3 module), VLANs work flawlessly. If, however, I replace the card, and use a 100 Mbit one (Intel/e100 or Realtek/8139too module), and don''t change the scripts, VLANs are not working. Why is it so? What is so fundamental in Xen networking that VLANs behaviour chang...

Hi, Can you tell why my vnic built on top of an aggregation of 2 NICs of 1 Gbit/s doesn''t report a speed of 2 GBit/s ? [root at nazgul /]# dladm show-dev bge0 link: up speed: 1000Mb duplex: full bge1 link: down speed: 0Mb duplex: unknown bge2 link: down speed: 0Mb duplex: unknown bge3 link: down...

Hi. I have 2 PC's connected with 1GBit NIC's. When I transfer a file from my File-Server(Redhat9.0, 256 SD-RAM, 300MHz PII, RTL8169 NIC, 2x Western Digital WD200JB RAID 0) to my Windows-PC(AMD Athlon XP 1800+, 1024 MB DDR-RAM, WINXP PRO, RTL8169 NIC, 2x Western Digital WD080JB RAID 0) with Samba, i get Speeds around 8-9MB/sec. I thi...

...is alway 100% CPU. The commands are shown as below. > > iperf3 -s -D > iperf3 -c IP -i 1 -P 1 -t 20 -M 1400 > > or > netserver > netperf -H IP -t TCP_RR -l 20 -- -O "THROUGHPUT,MEAN_LATENCY" > > host -> guest: > iperf3: > * With the patch: 27.0 Gbits/sec > * Without the patch: 14.4 Gbits/sec > > netperf (TCP_RR): > * With the patch: 48039.56 trans/s, 20.64us mean latency > * Without the patch: 46027.07 trans/s, 21.58us mean latency > > This patch also improves the guest transmit performance. > > guest ->...

...Microsoft RTC Library. In particular I am wondering what Ethernet capacity should I have in scenario of 30 people using Microsoft RTC Library for SIP communication (PBX is obviously Asterisk :-) ) concurrently (alaw codec being used)? What problems can be expected in such scenario? Would a good 1 gBit switch be enough to handle that (Asterisk box would be connected to that switch with 1 gBit connection, and computers with Microsoft RTC Library would be connected with a 100 mBit connection)? Thanx! Alex

Hi, I install a new 4 Port GBit Server with centos 6.3 and I'd like to use nic bonding. Searching for a good how to pinted to this page: http://www.how2centos.com/centos-6-channel-bonding/ My question: Is this the current, good way to bond the 4 ports? The other question: What should I set on the cisco switch for the Port...

Hi, I've a strange issue with the performance of file transfers between a Samba server and a Vista client. My configuration looks like this: fileserver: Samba 3.3 on FreeBSD 6.2 ----- gbit switch ----- workstation: Vista x64 When transfering files between the two PCs, I get abount 6.5 to 7 MB / sec. On my last Vista installation I got about 40 MB / sec. I've tried the following: - raw tcp transfer rates with netio: 40MB/s with 1kb chunks up to 100MB/s with 32kb in both direc...

Hello listmates, We are working on setting up two private networks linked by a public network which is fast (1 Gbit/s) but potentially insecure. Since the hosts on our two networks need to talk to each other, and do so securely, we have decided to use OpenVPN to connect them, making one gateway a server and the other a client. The connectivity part was easy to establish and worked like a charm. The only problem...

On Tue, 22 Oct 2002, Phil Doroff wrote: > So, I figured since this list is the most likely to deal with people that > push a lot of packets through Linux, and possible some via fiber I''d like to > know if anyone has any recommendations on which NIC to buy to replace this > thing. We have been using the Intel E1000 card with Intels drivers for some time with success. (the

...e 600+ Mbit/s. When I run an iperf test from node1 (client) to node2 (server) with default options, I have 300 Mbit/s MAX. The strange thing is that 300 Mbit/s was the limit with Tinc 1.0. I checked twice, both of nodes are now running tinc 1.1... Of course, when I do iperf without Tinc, I have 1 Gbit/s... sptps_speed report correct speeds (node1 is less powerfull than node2) : root at node1:~# sptps_speed Generating keys for 10 seconds: 597.41 op/s ECDSA sign for 10 seconds: 549.90 op/s ECDSA verify for 10 seconds: 470.60 op/s ECDH for 10 seconds:...

...s=100us and use the iperf3 to test > > its throughput. The iperf3 command is shown as below. > > > > on the guest: > > iperf3 -s -D > > > > on the host: > > iperf3 -c 192.168.1.100 -i 1 -P 10 -t 10 -M 1400 > > > > * With the patch: 23.1 Gbits/sec > > * Without the patch: 12.7 Gbits/sec > > > > Signed-off-by: Tonghao Zhang <zhangtonghao at didichuxing.com> > > Thanks a lot for the patch. Looks good generally, but please split this big > patch into separate ones like: > > patch 1: lock vqs one b...

Hi, recently I installed a new GBit connected iSCSI Storage to one of our fileservers. Redhat EL Linux 5.7 samba3x-3.5.4-0.83.el5, kernel 2.6.18-238.19.1.el5PAE, Dell Poweredge 1750, dual Xeon. The transfer speed is very very different, depending on the method I use. Currently I'm the only user accessing that server and there is...

...atch, qemu can set differently the busyloop_timeout for rx or tx queue. We set the poll-us=100us and use the iperf3 to test its throughput. The iperf3 command is shown as below. on the guest: iperf3 -s -D on the host: iperf3 -c 192.168.1.100 -i 1 -P 10 -t 10 -M 1400 * With the patch: 23.1 Gbits/sec * Without the patch: 12.7 Gbits/sec Signed-off-by: Tonghao Zhang <zhangtonghao at didichuxing.com> --- drivers/vhost/net.c | 106 +++++++++++++++++++++++++++----------------------- drivers/vhost/vhost.c | 24 ++++-------- 2 files changed, 66 insertions(+), 64 deletions(-) diff --g...

...atch, qemu can set differently the busyloop_timeout for rx or tx queue. We set the poll-us=100us and use the iperf3 to test its throughput. The iperf3 command is shown as below. on the guest: iperf3 -s -D on the host: iperf3 -c 192.168.1.100 -i 1 -P 10 -t 10 -M 1400 * With the patch: 23.1 Gbits/sec * Without the patch: 12.7 Gbits/sec Signed-off-by: Tonghao Zhang <zhangtonghao at didichuxing.com> --- drivers/vhost/net.c | 106 +++++++++++++++++++++++++++----------------------- drivers/vhost/vhost.c | 24 ++++-------- 2 files changed, 66 insertions(+), 64 deletions(-) diff --g...

...n running the tests, the vhost-net kthread of that VM, is alway 100% CPU. The commands are shown as below. iperf3 -s -D iperf3 -c IP -i 1 -P 1 -t 20 -M 1400 or netserver netperf -H IP -t TCP_RR -l 20 -- -O "THROUGHPUT,MEAN_LATENCY" host -> guest: iperf3: * With the patch: 27.0 Gbits/sec * Without the patch: 14.4 Gbits/sec netperf (TCP_RR): * With the patch: 48039.56 trans/s, 20.64us mean latency * Without the patch: 46027.07 trans/s, 21.58us mean latency This patch also improves the guest transmit performance. guest -> host: iperf3: * With the patch: 27.2 Gbit...

Hi, We have the following config: Servers -> BGP router (10 Gbit) -> BGP router (1 Gbit) -> BGP router (100 mbit) We would like to do the following. The server should first fill the 100 mbit link, then fill the 1 Gbit link, and then the 10 Gbit link, when traffic increases. The resverse applies when traffic decreases. I fou...

From: Tonghao Zhang <xiangxia.m.yue at gmail.com> This patches improve the guest receive and transmit performance. On the handle_tx side, we poll the sock receive queue at the same time. handle_rx do that in the same way. This patches are splited from previous big patch: http://patchwork.ozlabs.org/patch/934673/ For more performance report, see patch 4. Tonghao Zhang (4): net: vhost:

...m running a fileserver with smbd here. The server is a 64bit 2.8 GHz Celeron D with 2GB RAM, running 64bit Debian, Samba version 3.0.23c. It is running as a pure fileserver so its only CPU load is serving files. The client I am doing the tests from is WinXP Pro SP2. It is connected via Intel e1000 gbit ethernet (both the server and client use e1000 chipsets). I have done a raw tcp benchmark (using netio) and the network IS capable of transferring 120 MB/s. The problem is: The maximal transferrate when reading from the fileserver is limited to almost exactly 50 MB/s. The 50 MB/s are reached wh...