CentOS 5 Server :: NFS Performance With Files Not Yet Cached By The Server File System?
Feb 25, 2009
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?
So everytime i try and use the "yum" command. for some reason it doesn't go past this point: "loading mirror speeds from cached host files". i cleaned up the cache and rebuilt the OS again, and im still getting this problem. would this be a problem with my internet connection? I'm using CentOS 5.5.
i have been trying to complete the following project1) Configure a FTP server where we can upload and download files.........2) server must run at 9 pm & stop at 9 am automatically ............although the first task was easy ,i have no idea how to accomplish the 2nd task(not to mention I'm a new user)
I have configured a "Syslog" server on /var directory as a separate ext3 partition - to receive the logs and events from the clients & the firewall as well. The directory needs to grow dynamically as the logs are populated. Is there a way i can make the filesystem grow dynamically as and when the directory is full.
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;
Old server: access_log.1 100% 4192KB 1.4MB/s 00:03
New Server: 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.
mii-tool shows; 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.
Centos 5.3 includes Ext4 and improved support for encrypted file systems but it appears to be aimed at laptop/desktop systems, in that a password must be entered at boot time.
Is it possible to have a server with an encrypted root file system boot up without entering a password?
Mandos will do it... http://wiki.fukt.bsnet.se/wiki/Mandos ...by serving up the password from another server... http://packages.debian.org/squeeze/mandos ...to a client loaded into the initial RAM disk environment... http://packages.debian.org/squeeze/mandos-client ...but it's not available on CentOS, and is only in Debian unstable.
Is there a similar (or any) solution for CentOS?
In particular, I'm envisaging encrypted virtual machines being served passwords from their virtual host.
Alternatively, the data that *really* needs to be protected could be encrypted while the system core remains unencrypted. But then the keys to decrypt the file system must be stored in the unencrypted portion, so this is not an effective method.
I am administering a live web server i want to keep a backup of the access log file without disturbing the server performance. can anyone guide me how to to this. the size of teh log file run in GB so i will need to take a daily backup
It stores all my important stuff, as well as some music and movies.I use a second linux box in my living room to "stream" content via NFS or SAMBA share.The streaming tends to stop several times during playback, and needs to fill up its buffer again before continuing to play.I also have some Windows XP and 7 based computers that connect to this file server.I have noticed that directory listing is VERY slow, and there is a huge lag when I want to save/read a file from/to my home directory.
This is my setup:Ubuntu Server 10.10 64 bit (I have the same problem with 32bit ubuntu) 3 RAID5 arrays with 4 hard drives eachLVM on top of the 3 raid5 arrays.The Logical Volume i use is about 6.5TB, and I use the ReiserFS file systemThis LVM has grown over the years, and has had som replaced disks. So I have used the pvmove, and extend commands a bit.I have tried using IOTop and top to check if there is not enough resources available, but that doens't seem to be the problem.I haven't been able to find out why streaming over the network stops, but I know it is the server that causes the problem.Does ReiserFS have any performance problems with large logical volumes? Would changing to EXT4 or some other FS give any performance gain?
I have tftp-server running on Centos 5. Clients which are on the same subnet as the server are able to get and put without problems. I have a client that is across the internet that is having trouble getting files from my tftp server. A tcpdump reveals that the client is requesting the same file over and over again. In /var/log/messages, I am see the following error repeated over and over until the client finally gives up.
localhost in.tftpd: tftpd: read: No route to host
I've setup a Lamp Server for Testing, The Lamp Server is Up & Running on CentOs 5.5
I am now trying to setup a VSFTP server where local users can upload files to there home directory so that Apache can serve web pages straight from the directories of system user home/accounts giving users the ability to run their own web sites which are hosted off the main server [tutorial here: [url]
So far i have been able to serve/display index.html files from the users home directory [url] but so far i cant upload files to any user home directory, every time i try to upload a file with filezilla i get this error message: 553 Could not create file. Critical file transfer error
I have searched online for similar problems like mine and so far i've tried alot of the solution but none seem to work. I'm confused, dont know where i went wrong, i put the users in a group called ftpusers and here are the permissions on the users (test, ftpuser & testftp) home directory. have a look an tell me where i went wrong :(
Also the root directory where the web pages are served from is called public_html here are the permissions
Here is my vsftp.conf file can someone check it to see if i made any errors in there:
I run a webserver with centos 5 and like to change hardware. I run a 1u supermicro 6014t server with 4 *500gb raid 6 and like to downgrade to a smaler but more efficient server. The problem is this. I'dd like to transfer all the content and the whole OS to the new system, but how do I do that
I am kinda stuck while providing solution for the above problem. I have achieved the fail over using keepalived but not sure how can we replicate the data from one server to other seamlessly and have them in sync with each other. My prime requirement for this project is end user should not notice the fail over and replicated copy of data should be available on the secondary as well.
I have 2 computers on the same network that i need to link together to transfer files 1 is a web server the other is a minecraft server. the problem is that the file transfer will be constant as the minecraft server will constantly updates files on the web server and I dont want it to go to the router then to come back to the web server. I want to add a second network card to each computer and link them together and use this second connection to transfer the files is it possible?
We are trying to define an appliance for an application server so I would like to know which should be the best file system type for this kind of use, basically our web applications uses libraries of 50 KB and our web apps.creates temp and logs files not bigger than 3 MB.
I have a CentOS + Samba server and Windows XP client machines. Users, passwords and permissions are entered on the server machine.users and passwords ( same as on the server ) are entered in the XP client machine.When attempting to access a public file on the server using a XP client machine and the IP address of my server, I am asked a user name and password and none of the already entered seem to work. I cannot access the server file (prompted again and again to enter user name and password). What did i miss
Can anyone tell me in performance tunning of apache-tomcat and jboss application server?when I deploy some application in apache-tomcat the performance is say 100 users per second and incase of jboss it is even worst (35-40 users per second)i want to improve my performance 1000 uesrs per second..
On my local apache web server I had installed gnome desktop, because I wanted it to use as a TV. But when I installed the gnome desktop, my requests for web pages became terribly slow (4-5 seconds!). When I deinstalled the gnome desktop, the request where fast again. But I still want to watch TV on my server, so I wander if people know why the gnome desktop harms the performance of the server?
PS. with gnome desktop, ping was <1 ms, samba server worked like charm, wget localhost was <1 ms, but for some reason, when tried to get a webpage from my webserver to a remote machine, it took seriously 4-5 seconds to load a page.
I am hosting apache service on the CentOS5.4. I configure the Apache in default setting mostly. But keep getting complaints from others about the website download too slow, pdf cannot download at all, flash cannot play smoothly, etc.. But on my own machine, everything works fine. Is there any tool for analyzing this problem?
There is my problem ,after a wrong manipulation after uninstall syslog in centos 5.6 server i removed 83 packages:YUM,RPM,vim,ls..............so i can't even try to install a new package because i miss yum and rpm.
When I use rpm command it says an error like below:
rpm: error while loading shared libraries: libssl.so.6: cannot open shared object file: No such file or directory
Last I upgraded one of our cent 5 boxes which is running kvm with a mix of centos and windows VMs.After the update performance just tanked on the XP guest, but the others (including other windows VMs) are just fine.I checked with our good friend google and didn't really get any help there.We're hoping to NOT have to rebuild the XP guest, so I thought I'd check in here first.
I have a remote ftp serwer, witch many of disks, something SATA, some IDE... There are ext3 filesystems. And a lot of files and direcotories/subdirectories. Tell me, which filesystem is the best for serwer like this? I'm not interesting on efficiency... The most important thing is failure-free. On ext3 sometimes is problem witch 'dirty' filesystem, in that case I must handy run e2fsck to fix this. Is any option to automate this, or any power-down proof filesystem?
I have some trouble with my hp workstation xw4400 with an ATI FireGL 3300 and the X-Server. There was no problem with the graphical install routine and the graphical boot works fine. But when the system changes into the login-screen, then it results in a black screen and a more or less frozen system.
I need evaluate the ext3 file system performance; i need define:
- services provided - parameters and - the performance with different parameter values; for example, changin the value of the "data" parameter (journal, ordered, writeback).
I do not know what services ext3 provides. Well, i know intuitively that it provides services to read, write and erase files. But, there are anything more?. Where can i find the API?. Is the ext3 file system POSIX compliant?
I've setup my server by following a ton of goods, and it seems to work ok, but I need to start using my server for email in order to receive orders placed via my website. I've followed this guide - [URL] I followed the steps above, and tested the mail server via telnet, and all seemed to be ok. I tried sending an email via Squirrelmail, from firstname.lastname@example.org TO my working email email@example.com, but the server returned with the following message:
<firstname.lastname@example.org>: host mail.c1systems.co.uk[184.108.40.206] said: 550-Verification failed for <email@example.com> 550-The mail server could not deliver mail to firstname.lastname@example.org. The account or domain may not exist, they may be blacklisted, or missing the proper dns entries. 550 Sender verify failed (in reply to RCPT TO command)
I will be relocating to a permanent residence sometime in the next year or two. I've recently begun thinking about the best way to implement a home-based network. It occurred to me that the most elegant solution might be the use of VM technology to eliminate as much hardware and wiring as possible.My thinking is this: Install a multi-core system and configure it to run several VMs, one each for a firewall, a caching proxy server, a mail server, a web server. Additionally, I would like to run 2-4 VMs as remote (RDP)workstations, using diskless workstations to boot the VMs over powerline ethernet.The latest powerline technology (available later this year) will allow multiple devices on a residential circuit operating at near gigabit speed, just like legacy wired networks.
In theory, the above would allow me to consolidate everything but the disklessworkstations on a single server and eliminate all wired (and wireless) connections except the broadband connection to the Internet and the cabling to the nearest power outlets. It appears technically possible, but I'm not sure about the various virtual connections among VMs. In theory, each VM should be able to communicate with the other as if it was on the same network via the server data bus, but what about setting up firewall zones? Any internal I/O bandwidth bottlenecks? Any other potential "gotchas", caveats, issues? (Other than the obvious requirement of having enough CPU and RAM).Any thoughts or observations welcome, especially if they are from real world experience in a VM environment. BTW--in case you're wondering why I'm posting here, it's because I run Debian on all my workstations/servers (running VirtualBox as a VM for Windows XP on one workstation).
I am running an application that requires use of my /etc/hosts file. In it, I have my machine name and its LAN ip address. The program creates a service on a specific port, then attempts to connect to it based on the host name. So my hosts file has to be correct.I added the nameservers to resolv.conf and now my application will not run. My guess is that the computer is checking the name servers first, timing out then checking the hosts file.Is there a way I can tell the system to check the hosts file first, then DNS. I thought it should behave that way by default, but it does not appear to.
I'm planning to add 1tb sata disk to my lovely file-server under ubuntu 10.10,what i want is use this disk as additional storage for network user,indows and ubuntu?I mean when my ubuntu server down (worse case) I can easily take out the disk from ubuntu machine and plug in on windows machine