CentOS 5 Networking :: Poor Network Performance On New Server?
Jan 29, 2009
ok, we had to move one of our databases due to failing hardware. This box is newer than the old but it's just dog slow. 1st I thought it was mysql but now I am realizing it's the network. As a test, I tried copying a remote file to that box and the old server (located at the same co-lo, same provider), same switch, etc.Here are the results;
access_log.1 100% 4192KB 1.4MB/s 00:03
access_log.1 100% 4192KB 72.3KB/s 00:58
So now I see why people were complaining about webpage load times, etc. I can't figure out why the network latency. I looked around a bit, see below for some things, I thought mtu, nic speed, etc.
eth0: 100 Mbit, full duplex, link ok
eth1: 100 Mbit, full duplex, link ok[code].....
Are there other things I can type to test or provide more feedback somehow to get more information.
This is a thread I've moved over from the install forum and is hopefully more focused. Sorry if I have violated some protocol. Problem I have a new machine build configured to dual-boot Windows 7 and OPENSUSE 11.4. Network performance in Windows is very good but network performance in OPENSUSE is very poor.
I just installed CentOS 5.4 on a brand new DL160 G6. In order to get the data raided I decided to go with mdraid. But I see quite harsh performance hits, I have no GUI or anything and just the basic server installation, and even the console feels sluggish.
The output from getinfo.sh disk:
==================== BEGIN uname -rmi ==================== 2.6.18-164.15.1.el5 x86_64 x86_64 ==================== END uname -rmi ====================
I've just removed fedora 10 and installed CentOS 5.4 both x86_56 on my Lenovo ThinkCentre 9091-CTO workstation, and observed serious performance degradation while intensive I/O operations and huge load without significant CPU consumption in user mode with about 50% in I/o wait.For example if I do the "tar xjvf some_large_tar.bz" file and run vmstat i get the output below. This is the only cpu and io intensive process running. The load gets up to 6 on C2D CPU and the machine has unacceptable responsivness.
[root@f00 ~]# vmstat 5 10 procs -----------memory---------- ---swap-- -----io---- --system-- -----cpu------ r b swpd free buff cache si so bi bo in cs us sy id wa st
I installed on a Intel SR2612UR Server with integrated LSI Expander and a Adaptec 5805Z controller a Raid 6 Array with 12x 2TB Drives (2 ext4 Partition: 16TB, 2TB), but I get very poor read speed depending on the blocksize that I set it vary between 130 MB/s and maximally 170 MB/s which is really poor for a Raid 6 Array of 12 drives, on a similar Dell Server I get above 650 MB/s. The Adaptec Controller has the latest Firmware installed.
iwconfig shows that the bit rate is 130Mb/s and link quality is 98/100. I'm using the wcid network manager instead of defaul gnome one. I'm getting lots of packet loss and performance is very bad. The connection is practically unusable. I've tried installing the compat wireless backport package but that did not work at all.
i'm trying to run ubuntu 8.10 intrepid ibex on an old hand-me-down laptop that i got from a family member, and i've noticed that the performance is actually much worse than it was on windows xp professional (32-bit).
first of all let me give you my specs: ibm thinkpad r32 intel mobile pentium 4-m 2.0 ghz ati radeon mobility m6 (i think this is actually the mobility radeon 7000 igp) with 16mb ram 256 mb ram (pc-2100)
i understand that these are very low performance specs, but it feels like the computer is running very sluggishly even for those specs. the computer ran just fine in windows xp, but is extremely sluggish in ubuntu. it seems like it detected all the hardware just fine, but i feel like it may not be utilizing the cpu and/or video to the extent that it should be. a couple of places where it really seems to struggle is when first opening new programs, viewing flash intensive web 2.0 type webpages (i.e. videos), and listening to music/podcasts (with rhythmbox).
it seems like rhythmbox really kills my performance more than anything else, but the performance is poor all around compared to xp, and i feel like that shouldn't be the case. like i said, i understand that the specs are poor, but it feels like it's not even living up to those specs. i know that 8.10 is old and outdated now, but it's what i had laying around and i figured that it might perform better on this old deprecated laptop than 9.10 would anyway. am i wrong in this assumption? would 9.10 perform better for me?
I am running karmic and have wireless performance which is terrible on the EEE 1000HA I see it as low as 1mbit at times and others at 24mbit and briefly at 48 and 54mbits. running an Internet speed test with wireless I get pathetic speeds as low as 15Kbps, Its 5 feet from the wireless router ... and other machines that are wireless in the same area show 54mbits and perform great ... any one solve this problem with the asus EEE1000HA running on karmic?
I just installed Ubuntu 10.04 on a laptop that was given to me. It is having a lot of lag issues,especially when playing videos and visiting websites using flash. It's an Intel Pentium 4 2.4GHz machine. I think that it should perform better because I had used and AMD Sempron 2.0GHz machine with Ubuntu before and video playback was much better than this. I'm thinking that my problem is the graphics card driver. Here is the card that this machine has:
Code: :~$ lspci | grep Radeon 01:05.0 VGA compatible controller: ATI Technologies Inc Radeon IGP 330M/340M/350M The AMD machine was using a VIA graphics chipset.
I used the command "Xorg -configure" to create a xorg.conf file, hoping that might help. But it didn't. Here it is:
Is there any tweaking that I can do in the xorg.conf that might help? I don't know which of those options I should set. I also tried changing the driver to "ati" but that did nothing. found some info for settings with "man radeon", I'm going to try some of those out.
I have an ATI RADEON 7000 (taken from lspci) 64 MB graphics card. My computer has a 700 MHz Celeron CPU and 650 MB RAM with Ubuntu 10.04. Anything graphical is slow. I cannot even play basic games like SuperTux. I think it is a graphics driver problem. Will this card ever work well with Linux, what do I need to do?
I experience very poor desktop performance on my system. General clicking responsiveness is poor, taking over second or two to focus to a new window, move windows around, ... etc. The Xorg process constantly uses over 60% of the CPU even when I'm doing nothing, and when I do click around it will quickly go up near 100% usage. Performance is initially OK when I first launch into my Gnome environment, but it soon deteriorates within 30 minutes or so. Eventually, after days of being up and running, my desktop will crash.I am running Ubuntu 10.10 with latest upgrades. I have four monitors attached to my "nVidia Corporation G98 [Quadro NVS 420]" graphics card. I am running the "NVIDIA accelerated graphics driver (version current)" recommended in the Ubuntu "Additional Drivers" app. I get a fair number (hundreds) of these in my /var/log/Xorg.0.log:
though they don't appear constantly while my desktop is running (I assume they may come in batches?). Not sure if they're relevant. A separate issue, though possibly related, is the SpeedCrunch app (a desktop calculator) is guaranteed to crash my desktop as soon as it gets focus. Here's the relevant output of "lspci -v" which shows my graphics card:
03:00.0 PCI bridge: nVidia Corporation NF200 PCIe 2.0 switch for Quadro Plex S4 / Tesla S870 / Tesla S1070 / Tesla S2050 (rev a3) (prog-if 00 [Normal decode]) Flags: bus master, fast devsel, latency 0 Bus: primary=03, secondary=04, subordinate=06, sec-latency=0
So for the last, oh, three or four hours now, I've been trying to get videos to play properly in Ubuntu. I have the default player, I have vlc, I (apparently) installed mplayer, but it won't play anything at all.
I was having horrible screen tearing with standard definition .avi's in vlc, fixed that by setting vsync in catalyst control center to always on or whatever it is.
Now, I have tried to run a 720p x264 video. It PLAYS, but not well. Audio is fine, however video is all jerky in VLC, and in Totem it's just a mess of screen tearing (although the video does no jerk on that player).
I have just spent HOURS trying to get VIDEOS TO PLAY. This makes no sense. Playing a video should be the simplest thing in the world for any OS to do, but with Ubuntu it is like pulling teeth. I have NEVER been so frustrated while using a computer. What is going on here?
BTW, I installed every single thing needed to use mplayer but it still does not work. The player comes up but will not play any type of file.
My system specs: 2.2Ghz dual core (intel) 3gb ram 1GB radeon hd 4650 vid card asus ipibl-lb mobo
I was really enjoying Ubuntu until I got around to trying to watch some videos. Now I am maybe minutes away from going back to vista. At least on there I can watch full 1080p videos if I want with no problems.
I am running kubuntu 9.10 on a dell inspiron 14 with an intel GM45 graphics card. When I run 3d games like Nexuiz, openarena and tremulous I get really random performance. Sometimes things are totally playable with somewhere between 50-80 fps and other times I get maybe 4 fps and everything takes forever to load. These effects persists between logouts, X restarts and reboots! I get no errors when I run things in console either.I never really play games much but when something doesn't work...
I have an ATI Radeon x1300 graphic card on an Intel platform.Since the last reinstall my Debian Squeeze system shows very poor performance in glxgears,only 80-90 FPS. Last time I had a problem the kms setting in the kernel. I disabled the modding setting in GRUB and then glxgears showed about 900-1300 FPS. Now,the problem is back, even though I made the same setting in the boot loader.
i had recently loaded squeeze and had an issue with the 2d performance.i.e when being prompted for the root password, the shading slowly draws down the screen several times before stopping at the final darker shade. i then added the linux-firmware-nonfree package. all worked extremely well, even compiz, but i don't really care about compiz. i just loaded it to see how it performed. i then distro-hopped a bit and when i came back to squeeze the first thing i did was add the package, but the video is acting like i haven't added the package. i've searched for an answer, but have not found anything recent to indicate if xorg was upgraded or what.stable lenny works fine, but i'd rather have the nice console fonts when not in x and more up to date apps like gimp and xsane in squeeze.
I use chrony on my laptop thinking it would be better for it than ntp because I'm frequently connecting and disconnecting from wireless cafe access points and going in and out of suspend mode. But I've also noticed that if chrony is started before the access point is connected it never syncs to the time servers. I have to manually restart it via the service command after I connect. This doesn't seem right to me, if chrony fails to find a network at start time, doesn't it periodically try again ?
I have a weird performance issue with a centos 5 running a nfs server and a rh8 client. I think the fact that it is rh8 client should be downplayed. It is just that with rh8 client the performance degradation seems more clear. See test details below OS in server is Centos 5 x86_64 kernel 2.6.18-92.1.22.el5
1Gb connection between machines File to test over NFS is a 1GB file. First of all I wanted to measure how the network alone performs while using NFS. So in the server side I run a "cat" command on the 1GB file to /dev/null. Please note that the disk read speed is about 98MBs. At this point the file system has the 1GB file cached in memory. In the client side a "cat" on the same file gives me a speed of about 113MBs. It seems then that the bottleneck in this instance is the network and it is very close to nominal speed. So the network performance is really good. (BTW I know that the server got that file from cache because a vmstat or iostat shows no disk activity.)
The second test is reading from disk with no caching involve. In the server I flushed the 1GB file from the memory. For instance by reading another 5GB file and I repeat the same thing as above in the client (a cat on the 1GB file). Now, the server has to go to disk.(vmstat or iostat shows the disk activity). However the performance, now, is about 20MBs, I was expecting something closer so 90MBs. (since the reading speed in the server in the first test showed 98MBs).
This second test was repeated for ext2, ext3, xfs with no significant differences. A similar test using a RH8 NFS server and client gets me close to 60MBs for a 1GB file not cache by the file system in the serverSince network speeds and disk read speeds are not the bottlenecks ... what or where is the limiting factor then?
I wrote a script which sends the server,files from /proc/ like dev,netstat,loadavg etc of a client. i want to calculate the network load and the overall cpu performance of the client using the information from the files.I donot know how to calculate that as i have too many values in those. which values will be useful and how to calculate?
I am looking for a gigabit network card for my centos 5.4 server. I am looking for something known to work well with linux. I have been on the bestbuy site and I found a DLink (DGE-530T) card with support for linux from the vendor but after reading feedback from users with that card I am not so sure it is linux friendly. I am now thinking of buying online.
I'm setting up my server under CentOS 5.5 (text mode) and I installed cherokee server but I couldn't reach it with the ip given by ifconfig. So I figured it might be an problem within cherokee. I also wanted to install webmin so I did that to see if I could reach that one. But also the webmin server is not reachable (I know the port number should be behind the ip ). So if I look up ifconfig I see the server has got an local ip (192.168.1.42) but I can't reach it from another computer in the same local network.
I have OpenVPN running successfully on a CentOS Linux server. All remote clients connect without a problem and can ping the server LAN (10.5.0.0/24) . The server address is 10.5.0.1. All network shares on the server are available to the remote clients via SAMBA shares and this works well.The problem is that I am unable to get the remote clients to access services on the LAN clients. For example, there is a webserver running on a Windows XP PC (on the server LAN @ 10.5.0.2) with no firewall enabled. The remote VPN clients can ping this webserver at 10.5.0.2, but cannot browse the webserver at [URL]. All clients on the server LAN can however browse the webserver. The remote clients are using Windows XP and VISTA with OpenVPN 2.1.1.
I am new to VPNs and networking, but from my research, it seems as if this may be a routing issue. I would appreciate any help you may give in getting the remote clients to access the services on the LAN clients (other than the server @ 10.5.0.1).
I'm having a bizarre problem with FTP transfers from my CentOS 5.3 boxes, All of my CentOS boxes appear to be limited at ~10kb/s when connecting to any FTP server outside of our network. We have no network infrastructure which would cause this, however when I use a windows based machine it is able to connect fine.
I took my laptop running Vista, and rebooted it onto a CentOS 5.3 LiveCD, and same issue.
I have checked our iptables, cleared the rules, removed the kernel modules, checked CBQ/TC it looks like nothing is limiting this. Also, other protocols work fine. Both the windows and linux boxes used passive transfers for it.
Is there anything other than iptables/CBQ which would be on a out of the box install of CentOS I should check? Is there any kernel settings for NAT connections which may cause this?
The internal network is behind nat done by the PC Router.The TP Link is recieving wireless signal from outdoors and it has switching and basic routing capabilities. I'm using the PC router for better routing options.PC Router (or R for short) is a triple-booting machine - Linux, FreeBSD and Windows. It has two lan cards - external (ext_if) - 100Mbps Realtek 8139 and internal (int_if) - 1Gbps integrated Realtek 8169.The problem is that all traffic from R to the network is slow - about 5-20K, while the traffic in the oppoiste direction is all right - about 10MB that is fine for 100Mbps cables, NICs and switches. The problem persist no matter the OS the pc R is running.I've tried some debugging on the situation as follows:
- put another PC at the place of R - everything is fine. That exclude the possibility of damaged cables, RJ-45s, switches and etc. - connected both of the NICs to the Internet while the internal network is being disconnected and they both work fine (no delays) - traffic shaping is not running - there is nothing in firewalls except NATing the internal network (and it is working fine). Actually these firewall rules have been operational for more than months and everything was fine untill a week or two ago. - changed the internal NIC with another - connected the internal network directly to the TP and all of the PCs are getting good network performance. Then connected the R machine to the TP as well and there was good performance between the internal network PCs and R. - R has good performance to the TP. In fact everything has good performance directly to the TP (when not connecting trough R). - the problem persist only between R and machines from the internal network.
I've just installed Karmic 9.10 to a new 500GB sata in a friends PC and it boots and runs fine; internet and everything just works. Just reinstalled XP-SP3 to old 80GB pata drive in same PC, it boots ok, but has no sound, poor graphics and network is limited to 1394 - no ethernet.
I built this PC about 3 years ago and it had been running XP with SP2 then SP3 installed, and everything worked fine. So over the past day I have installed XP-SP3 (slipstreamed disc) in it 3 times now, then went back and tried XP-SP2 (earlier slipstreamed disc) twice with same result - no ethernet, poor graphics, no sound?
But it all works fine in Karmic?
I ran Karmic's disk utilities (Palimsest) on the old 80GB and it tested fine, no problems at all.
PC comprises Gigabyte M55plus-S3G m/board, AMD 3800+ 2.4Ghz CPU, 1 GB RAM and a 64MB NVidia graphics card (can't recall model)
Is it possible MS built 'crippleware' in to XP, or could there be a hardware problem that Karmic didn't detect (doubt it)
Karmic is going to be the main OS now, so I don't think the loss of XP is a problem, but friend still wanted to be able to boot XP, even though XP is installed in Virtualbox in Karmic (I did this by importing a previously saved XP 'appliance').
My mother has Windows Vista and i have linux ubuntu. She has a special verizon card that she inserts into her laptop for internet. My computer also has an internal wireless card, but the signal here is very poor. Supposedly, among windows computers, I would be able to get a flashdrive, and with a little program uploaded from my moms computer, set things up using the flashdrive on my computer to share the internet that she pays good money for =/ However, it wont work with ubuntu, which isnt in the windows inner circle. When I open the executable file with WINE it says that it cant run wireless network setup "on this version of windows". lawl. I was wondering, is there any way around that? Is there anyway to network with my mothers internet?
I have a server that is on both a standard network and a virtual network, as follows: server1 attached to standard network server1 acting as Dom0 with two linux DomU guests (under Xen) I only have one network card. How do I configure server1 to have a different hostname on the standard network than on the virtual network? Here are the relevant network configuration files for server1:
I am attempting to setup a network to network VPN tunnel between our main office and a temporary location. This location need full VPN access back to the main office's network.Anyhow we have spent about 3 solid days attempting to make this work without any great success. Here is our network scheme for these two devices.
Network A (Main Office) (OpenBSD using isakmpd) Network: 172.16.8.0/24 External IP: 184.108.40.206 (obviously not the real IP)[code].....
I just upgraded from Ubuntu 9.04 64-bit, to CentOS 5.5 64-bit and my RT-73 USB network card doesn't seem to want to function. It always worked fine in Ubuntu by default (plug and play). Is there some setting I need to make to get this working?Even BT-3 (which is quite old) recognizes the RT-73.