Does anybody have experience with linux tuning. I`m realy interesting about sysctl.conf tuning settings for batch(3d rendering, phisycs simulations, etc.) servers. Does anybody has an experience with linux tuning - I mean memory and CPU settings for heavy loaded systems. What kind of settings You have in Your clusters ? I`m working with Red Hat Enterprise 5 x86_64.
View 2 Replies
My sysctl.conf in /etc isn't loaded at boot, it does however get parsed with the command # sysctl -p I believe this problem started when I got the 3.0.0 kernel just a few days ago. Does everyone has this problem? Then it's probably a bug.
My system:
Debian Testing (Wheezy)
3.0.0-1-amd64
up2date
Last week I attempted to get "up to speed" with my Comcast cable connection... Ubuntu 9.10, Dell Vostro 400 desktop, Firefox 3.6.13... Comcast says I should have 12 Mbps connection... if I get 1.0 Mbps, I'm doing good... they just tested everything, and said everything is fine on their end. They use [URL] and connects to a server in Chicago, 60 miles away. That gets fantastic speeds, and it's a durn shame the internet doesn't store all its files there!! I use [URL] for my tests, and it uses a server in Dallas TX.
I go to my girlfriends house, and her AT&T DSL line has d/l speeds of 4.5 Mbps or better!!! She's running XP Pro on a Dell machine. So, started digging on the web and thru the forums, and found this:
[URL]
But, like ALL too many things, it's dated... it's from 2008... I've set my settings to what is there, and disabled ipv6 in Firefox. Hey, now, I'm sometimes up to 1.4 Mbps!! Also found this, but no date...
[URL]
Reading forums, I see that folks have said there is a network connection problem with 9.10... and then I see that others are saying the same thing about 10.04 and 10.10!! I have 10.10 on my laptop and had to fight to get its Atheos card to be recognized. Running some tests [URL] gives me weird results: Download 2.64 Mbps, Upload 4.12 Mbps. NOT what it should be. Similar results from testmy.net.
Dunno exactly what info is needed... Speedguide.net gives me results below, but I've tried changing numbers (says my RWIN is low) and nothing changes:
--------------------------------
TCP options string = 020405b40402080adf1dca100000000001030306
MTU = 1500
MTU is fully optimized for broadband.
[code]....
So, today, find, once again, that I'm d'ling in the range of 90/KB/s (719 Kbps)... disgustingly slow. I go on my HP laptop and run the test, and it says 1.6 Mbps. So, desktop directly connected to router is not even 1 Mbps, and wireless connection is faster? Neither of which is close to what I should be getting...
Like in the subject. Does anyone knows how to do it without restart
View 1 Replies View RelatedOn a production Centos 5.3 system, I want to raise the hard & soft limits of open file handles from 1024 -> 8192 (not a "biggie", I'd think) Right now, "sysctl -a | grep file" shows fs.file-max=463144 (a default, I'd guess) I'm guessing file-max is the maximum number of open file handles on the system, vs the per-user limits seen with "ulimit -Hn" and "ulimit -Sn". Right? If so, I shouldn't think I'd have to touch this on a server with few users.
Also, after doing a lot of reading, I still don't understand the mentions of needing to also add: "session required pam_limits.so" to /etc/pam.d/loginor adding "session required /lib/security/$ISA/pam_limits.so" to /etc/pam.d/system-auth Maybe I've gotten off into the deep weeds in goggling about raising file handle limits.
I made some change to my sysctl.conf file and it they doesn't seem to load at boot? Each time I boot I need to send a sudo sysctl -p command to load the new parameter!
View 1 Replies View Relatedim trying change my etc/sysctl.conf file but it won't let me as its read only. how to i change this?
View 2 Replies View RelatedHow do I make a change to this file? More specifically this is what I am trying to do.
Add the following line to /etc/sysctl.conf
vm.swappiness=10
How can I find the size of units in sysctl.conf e.g whatis the size of the shmmax variable i.e. is it byte kb , Mb etc....???
View 8 Replies View RelatedDue to a change in how programs in Linux are allowed to use memory, before using SheepShaver you need to set a variable in the file /etc/sysctl.conf Add this line: vm.mmap_min_addr = 0 but when i add the line in my text editor it says i cant save
View 8 Replies View RelatedI've just installed Fedora 13 and I have a question. How do I tune my tablet? I've tried to set threshold and aspect in xorg.conf just like in Fedora 11, but it doesn't work in the current release.
Here's a part of my xorg.conf:
I also tried 'xsetwacom' command, but I get errors.
I have a query on mod_rewite/apache/.htaccessIt is like this:Suppose a company have a website www.abc.com,when a user types in this URL in his browser he should get a login and passwd prompt say he enters username as user1 and some passwd, upon successful authentication he should get redirected to another url similary for user2 and user3...mod_rewite is loaded htpsd.conf has "rewrite engine on" directive enabled.
View 1 Replies View RelatedI'm running a linux cloud server with the following config
1.2ghz Processor allocation
752MB Ram
The site loads slow and clicking a link almost freezes the page for a second. Also, the page loads could be much faster. We've been running mysqltuner and have pretty much optimized all slow queries. Is there anything we can do to fine tune the server for faster and more responsive?
Httpd.conf
Timeout 20
KeepAlive Off
MaxKeepAliveRequests 100
KeepAliveTimeout 5
<IfModule prefork.c>
code....
I just set up a new CentOS 5.5 system (using the 5.5 DVD, yum updated all packages to latest) which unfortunately due to various issues and most critically availability, has an ATI-4350. The install went OK but X does not detect the card properly so it's using the slow VESA driver. I followed the instructions here [URL] to download and install the ATI driver. It appeared to be correctly installed but not used.
Display still detects my monitor and 4350 as unknown and using some "Vendor supplied driver". Yet under the "Dual Head" tab, if I would to enable it, the ATI-4350 comes up as an option, hence implying that the driver was corrected installed and the card is actually detected. I suspect it might have to do with my Xorg.conf, although trying to edit in several ways didn't make it work.
I have a number of CentOS servers with latest 5.xI have 3 nameservers in the resolv.conf files. All 3 nameservers test out fine when checking for domain lookups.I'm having some trouble with ns1 and shut it down.l None of the CentOS machines fail over to the ns2 & ns3 entries. Basically everything stops resolving even though the other 2 nameservers are alive and well.
View 1 Replies View Relatedwe having more than 5000 users and will have 7 squid proxy servers with high end configuration upto 4gb ram n 320*5 HD in rhel4&5 most of them complaining that at peak hours their browsing speed is slow but we are having 1gbpgs link at peak hours i.e when established connections r flowing more than 550 browsing gets slow how to do fine tuning are squid is only responsible to access upto 600 connections
View 2 Replies View RelatedThere is a tool appeared in repository called ktune; The purpose is to adjust some sysctl.conf settings to improve server speed on servers with heavy load. What is this tool for if one can achieve the same with the configuration file added to system startup? Or ktune is just such file?
View 1 Replies View RelatedI am currently reading [URL] its an old document from 2006, so i am not really sure how much information in it is still valid.
View 1 Replies View RelatedI've been trying to set-up/tweek these param's in Apache to a setting suitable to the server for the amount of memory. When i look around some people say, hey.. just look at the memory used per process and then divide that by the amount of memory available and you get the number of processes that can be handled by Apache in one go before it starts swapping.
Well, for this i'd done this calculation and for me it turned out to be 200 approx concurrent connections. Well funny thing is, out MySQL server had a slow down so the Apache servers were running at approx 450 concurrent connections and weren't swapping in memory etc (still had 600MB free not including what was available in Buffers/Cache - 'free -m')... Thus if i had have set the limits to 200 then people would have been not getting to the site, so i'm kind of pleased that i happened to not have the time to set this yet.
My intention is to have EngineX on the frontend handling all static files, and Apache + mod_php in charge of handling PHP requests. I have optimized nginx to be as efficient as possible in handling static files, but have very little experience with Apache. Since Apache would only be processing PHP requests, would the standard Apache optimization guides suffice or would it best to configure it differently?
PS: this is a dedicated file server, the database is hosted separately.
I have an enormous quadcore machine with 16gb ram and dual gigabit NICs. It used to be for MySQL but we have upgraded the whole database infrastructure so now this server is left floating. I had the great idea of turning this into a reverse-proxy (using apache mod_proxy) and it really handles a ton of requests. But I have a feeling that we are not getting the most use out of what it can offer.
Our traffic consists of a few thousand very small (less than 10 byte) ajax calls per second, and frequently I find we are running out of kernel allocated network stack to handle all the requests. Often we get the kern.log warning "possible SYN flooding on port 80. Sending cookies." and other things like this. Obviously we are not getting SYN flooded, we just have very high demand.
So far I have found a few kernel tuning guides to tell the kernel to allocate more of the base system memory for networking but every guide I have found has been for the purpose of increasing the performance between WAN links (direct backbones between offices etc) and usually with very large file sizes being the priority. One such example (and great) write up is here:
cyberciti.biz/faq/linux-tcp-tuning/
I was hoping some people could provide further input, such as along the lines of disabling nf_conntrack (to speed up socket set up/tear down time) or anything that will speed up a high throughput proxy like mine. Any links to studies or benchmarks between different configurations or hardware gets extra points!
I've been scanning the apache2 docs for the past few days and have not come up with an answer my following issue:
In my httpd.conf file, at the very end, I have the line
Include conf/vhosts/vhost_*.conf
However, when I run apache checkconfig or try to start apache, it gives me the error:
httpd: Syntax error on line 993 of /etc/httpd/conf/httpd.conf: Could not open configuration file /etc/httpd/conf/vhosts/vhost_1.conf: Permission denied
It appears as if the Include line is correct - in terms of it grabbing the first virtual host conf file. However, I'm confused on the permissions. the /etc/httpd folder is owned by root:root, as are the subfolders. As a test, I chown'd the conf/vhost folder combination and all the vhost files to apache:apache to see if that made a difference, and it appeared to make no difference at all. The log files don't contain anything (assumed because apache isn't starting). If I place the contents of the vhosts in a singular vhosts.conf it works - with the permissions set to root:root. I'd like to avoid having to use one vhosts conf for the configuration I'm trying to achieve - as it would make my life a lot easier.
Can I run/compile programs on my remote server and control it using LAN? How do I do it?
Long Version:
I have a spare computer here. It's rather powerful for my daily needs (Athlon X2 6000) and I want to set it as my HTPC/Server. Don't worry about HTPC, it got Digital Audio output and a Radeon HD3200 with HDMI out, outputs 1080p pretty well under Windows (I'll setup it for Ubuntu when I get everything straight). So, I thought "Well, I think it's going to be overkill to let such machine as a HTPC only. I'll use it as a server too!". So far so good, but I don't know anything about servers or such. I would like it, as a server, to compile huge programs and handle big compressions (I'm actually with a Celeron ULV 1.2GHz netbook for such tasks, takes ages). Also, it would be pretty nice if I could control the server with my netbook. Like, Start/Stop music/movies with my netbook, control the Boxee/XBMC (Media Players) with the netbook, and, if possible, control its mouse.
Btw, will Ubuntu 10.10 support Hardware Acceleration for ATI Radeon HD3200? Over Windows' DXVA it works OK.
I want to using ubuntu 9.10 karmic koala. In that i want to see the file /etc/X11/xorg.cong file. But i didnt find that file in my distro. So please can anyone tell me how to see that settings and if i want to edit that how to do that?without seeing the format and alues in that file i cant add that file.
View 1 Replies View RelatedI'm running Kubuntu 11.04 on a laptop with dual monitor setup. I have Nvidia graphics card and I've successfully configured TwinView for the monitors. However, after saving the settings to xorg.conf (using the nvidia-settings application) X should use both monitors after boot, but only the main monitor is used. I first thought that X didn't read xorg.conf at all, but when I put some illegal statements into the file X wouldn't start and gave an error about the illegal statements. It is thus clear that X does read the file, but it just doesn't seem to use the settings in it.
Here is the contents of my xorg.conf file: [URL]
I want to using ubuntu 9.10 karmic koala. In that i want to see the file /etc/X11/xorg.cong file. But i didnt find that file in my distro. So please can anyone tell me how to see that settings and if i want to edit that how to do that?without seeing the format and alues in that file i cant add that file.
View 3 Replies View RelatedI want to using ubuntu 9.10 karmic koala. In that i want to see the file /etc/X11/xorg.cong file. But i didnt find that file in my distro. how to see that settings and if i want to edit that how to do that?without seeing the format and alues in that file i cant add that file.
View 3 Replies View RelatedI have setup a box using RHEL-5 inside a private network, no outside connections, and I've got a Symmetricom bc635PCI-V2 clock card installed and working. It's getting GPS time via IRIG-B feeding the PCI card from a TrueTime GPS receiver. I need to setup the NTP software to use the time from the PCI card. Which means I need to setup a /dev/refclock-? symbolic link to the driver as far as I know? I can't find any documentation on the bc635 card that associates the refclock to the driver. Does anyone know what settings I need to use in the server line of the ntp.conf file?
Server 127.127.<type>.<unit>
let me know how to clear cache memory ( RHEL 5.1 ) as it consumes almost 100% physical memory.
View 3 Replies View Relatedwe found that if we use 'top' to show the memory usage of a server (SuSe Linux 10), we can get virtual memory usage as well as 'Resident memory' usage. For virtual mem or a particular process, it is around 1.1GB, which is large but for resident memory, it only consumes 300MB. Are there anyone who knows what the differences are? I would also like to know whether the difference (1.1GB - 300MB) = 800MB are actually available for use by other applications in the system.
View 1 Replies View Related
