General :: Size Of The Library / Executable Is High In Compared To Solaris
May 18, 2011
We have a 32bit Gui application created using C++. We ported the application from Solaris to Linux. Issue we are facing is the size of the library and executable is very large in LINUX compared to Solaris. Red Hat Enterprise Linux 5.4 is the Linux version we using. Please find a sample dynamic library created. We would like to know the following behavior of LINUX is normal or not. Consider we created two files test1.cc and test2.cc. Both having a single line of code.
I am able to build a shared library under solaris with /usr/local/bin/g++ -G -o output.so file1.o file2.o file3.o. How do I build the shared library under linux using the same files? I have tried to use the same command /usr/local/bin/g++ -g -o but I got some undefined references, even if those references are defined in one of the object files.
Most of my many Linux installs boot up to a memory use of 170-190 MB with no open or running programs. But with Ubuntu 9.10 it shows; 305-310 MB and the top RAM use item is the; compiz.real, which I think is a display desktop effects application. I have the nvidia video card driver installed, and that nvidia X-Server configuration tool. Also I can not find where that compiz options is at, ( the display options in system, preferances does not open, and says to use my video card tool ).
I am trying to get a 32-bit executable to run on 64-bit Ubuntu. I had to install multilib, and then when I ran the executable, I got this error:
./x86/bin/target_base_mac: error while loading shared libraries: libxml2.so.2: cannot open shared object file: No such file or directory So I installed libxml2, but I still get that same error. The file does exist:
Code: [andreas@loony /tmp]$ ls -al total 40 drwxrwxrwt 4 root root 4096 Jul 14 10:28 . drwxr-xr-x 28 root root 4096 May 18 10:55 ..
A colleague told me that this does not work for shell scripts (even though apparently it does work for shell scripts under Solaris). However, this is not the problem per se, because I discovered this problem when using a binary program that needs the s-bit feature. I only made the small shell script to make sure that I understand everything that is going on and that it is not the binary program that is behaving badly... but I do believe that the problem is not in the program but in the operating system.
Set uid works. It is only set gid that does not work. That is, setting the s-bit for the owner works, but setting the s-bit for the group does not.
i am using classpath-0.98,jamvm-1.5.4 and arm9 cortex processor. so my question is after install classpath and jamvm on arm9 , i am getting around 30MB FAT file. so tell me some tips how to reduce the size of FAT file as much as possible.
I've a high resolution monitor(2560x1440) on my laptop running Debian testing and would like to change the font size in X. I manage to change most of the fonts to a readable size through the openbox configuration manager. But the font in my login window and for example in apps like vlc is still very tiny. How this could be changed ....
I am have upgraded from 9.04 to 9.10 in my laptop. After performing the reboot, the shell/console resolution went very high and the font size went too small. How to regain the old console shell resolution as in 9.04. I require this urgently as my laptop suffers the white screen problem. Switching between Ctrl+Alt+F6 and Ctrl+Alt+F7 I could get back the screen as the change in the resolution switches off and on the screen, so that I can negotiate with the white screen problem.
Why the thread stack size can not be changed after calling pthread_attr_setstacksize & pthread_create in a dynamic library? Detail: I write a file thread_factory.c and plan to build it and produce a dynamic library (libthread_factory.so) In the thread_factory.c , there is a routine
And after this, there is application, it will call fct_thread_create(STACK_SIZE_256KB), and then call pthread_attr_getstacksize(), but the stack size return always be a fixed value 0xa01000. (I tried this on Fedora12) But if I build the application source code with the file thread_factory.c directly, the stack size return is right as my expect. I checked the source code of glibc about the routine pthread_create() as below:
Debian lenny, old install (I've upgraded to lenny when it was just about to become the stable release), versus windows 7, fresh install.Comparing browsers speeds with numion.com/Stopwatch.html, I had results such as:Iceweasel (firefox) on linux: from 9.154 seconds to 21:860 seconds (the same webpage, reloaded)Firefox on windows: 4.32 seconds - and never much slower than thatThe fastest browser on linux was Opera, ranging from 8.562 to 5.503 secs to load the same page, but even internet explorer beat/match it with its timing of about five seconds.
I have not other browsers on windows; on linux there is aroraonqueror (KDE3), kazehakase, chrome, and dillo, besides text browsers. I didn't test on dillo; Kazehakase and chrome were the only ones which had nearly decent results, but still very bad, 11 to 13 seconds for chrome, and 21 for kazehakase. Konqueror just seemed to never finish to load the page, I gave up when it was still loading somethingfter nutes and 5 seconds.'ve emptied the cache every time I would test, and I was running almost only the browsers and not much else. Whatever comes by default on windows, and on linux, I was on openbox, with nothing much going on I guess, I think the most memory consuming processthe time, besides xorg and the browsers themselves, was dictd.
I've researched a little bit about, but not enough to make a list of possible things to change in order to improve the speed on linux. Most of the time there are people just agreeing that on windows the rendering is faster, and other people saying that with them is the opposite, with some minor variations like people saying that linux is faster for plain downloads while windows is faster for web browsing due to better graphics.
(by the way; I haven't installed any graphic card driver on windows, which is still running on 1024x768, while linux runs on 1280x1024, with the "nv" generic driver, without fancy options, not supported by my old card) The closest to a suggestion of possible solutions was someone saying tha compilation may affect performance, I guess it was both about kernel compilation, and the web browsers themselves.I'll google a bit more about how to "compile for speed", both kernels and programs (maybe the x server
i recently purchased my second laptop, primarily for linux. When i chose it, my main concern was battery life. Just to make a side note. When i say battery life, i mean how long the computer takes until the battery goes flat. Not how many years/ect it takes till the battery will no longer hold charge.
My new computer claims to be able to get 10 hours. Although it's a bit off, i get a satisfying little bit over 6 hours, from full charge. This is running Windows 7. I couldn't wait to put Linux on my new computer, i have, but it just isn't satisfying because i only get about 4 hours while running linux, tried three different distros, and all roughly the same.
i want to upload my iso collection to adrive(.)comi have a slow upload and i want to split each iso file in chunks of 100 MB so they upload while every browsing session of mine.i figured i should use split and cat commands to do that.but i cant afford to upload some corrupt archives, so how may i go about checking the small chunks to the original file before uploading
I have installed Wubi (Ubuntu 10.10) recently. It takes more time to boot than Windows. But my main concern is that my browsing speed is much slower compared to that on Windows 7. How can this be resolved?
I have Preinstalled Xp on my system.I have installed Solaris in one of my unused partition.when i installed the fedora 12 i didnot get the options for solaris booting though i have used different partition for solaris and fedora.How can i get the options for solaris or else i have made a mistake in installing fedora. In either case please guide me though how irritating it may be to guide a newbie.Also if i want to use Archlinux with all three above how can i do it.
What is the equivalent of read -r (solaris command ) in Linux ? read utility in solaris will read a single line from standard input and -r option is used not to treat backslash () as an escape character .
i have a linux mechine, in that i want to install solaris throug xen virtualization. (solaris content is in CD) while i am doing this there is an option "local install media" in installation method it was not highlighting so i can't install this. then what can i do now.
I am currently trying to use Kommander editor to create a GUI form to call the bash scripts that i have created. However, when i try to run it on Solaris 10, it says "Failed to execute child process kmdr-editor".
first of all, i will be glad if i can get prebuild toolchain for target=arm1176jzf-s on host= sparc-sun-solaris2.10. ( i hav browsed but can't find prebuild one) so, i tried to establish by myself i hav established binutils first, but while trying to configure& build gcc(gcc4.4.0) , i was interrupted with following error.. error message: this error has come while building boot strap gcc for cross complier tools chain
checking build system type... sparc-sun-solaris2.10 checking host system type... arm-unknown-linux-gnu checking target system