Skip to main content

How to use gdb in Ubuntu Terminal

Here's a practical, minimal guide for using GDB in Ubuntu terminal — from launching to setting breakpoints and navigating your code. 🧰 Step 1: Compile with Debug Symbols Use -g and disable optimizations ( -O0 preferred for debugging): bash Copy Edit g++ -g -O0 -o myprog myprog.cpp 🚀 Step 2: Launch GDB bash Copy Edit gdb ./myprog You'll see a (gdb) prompt. 🎯 Step 3: Set Breakpoints You can set breakpoints in three main ways : ✅ a. At a function gdb Copy Edit (gdb) break main ✅ b. At a specific file and line gdb Copy Edit (gdb) break myprog.cpp:42 ✅ c. At a method in a class gdb Copy Edit (gdb) break MyClass::doSomething If the symbol is mangled (C++), GDB usually demangles automatically, especially if compiled with -g . ▶️ Step 4: Run the Program gdb Copy Edit (gdb) run 🧭 Step 5: Navigate Command Meaning next or n Step over current line step or s Step into function call finish Run until current function returns continue or c Continue until...

Gcc compilation using .h & .c file (chatGpt response)

mymem.h hs declerations/ mymem.c hs implementations of those declerations n also other various static fn Now I hv main.c that includes mymem.h what will be gcc compilation command to generate main.o n then main.run file in ubuntu
ChatGPT said:
ChatGPT

To compile main.c, which includes mymem.h and links with mymem.c, you'll need to follow a two-step process:

  1. Compile the .c files into object files (.o).
  2. Link the object files to create the final executable.

Here’s how you can do it using gcc in Ubuntu:

Step 1: Compile the .c files into object files

bash
gcc -c main.c -o main.o gcc -c mymem.c -o mymem.o
  • The -c flag tells GCC to compile the source files into object files (.o), but not to link them yet.
  • The -o flag specifies the output file name.

Step 2: Link the object files and generate the executable

bash
gcc main.o mymem.o -o main.run
  • This step links the object files (main.o and mymem.o) together to create the executable file (main.run).
  • The -o flag specifies the name of the output executable.

All-in-one command

If you prefer to do it in a single step, you can also compile and link in one command:

bash
gcc main.c mymem.c -o main.run

This will compile both main.c and mymem.c and link them to generate the main.run executable in one step.

Notes:

  • If mymem.h is in a different directory, you’ll need to specify the include path using the -I flag. For example:
    bash
    gcc -I/path/to/header main.c mymem.c -o main.run
  • If you're using any additional libraries (like pthread, m, etc.), link them with the -l flag, for example:
    bash
    gcc main.o mymem.o -o main.run -lpthread
------------------------------------------------
now if both main.c n mymem.c contains int main(){...} fn will gcc -c main.c -o main.o gcc -c mymem.c -o mymem.o gcc main.o mymem.o -o main.run give some error during compilation or while invoking main.run?
ChatGPT said:
ChatGPT

Yes, having multiple definitions of int main() in both main.c and mymem.c will cause a linker error when you try to link the object files using gcc main.o mymem.o -o main.run. The reason is that the C standard requires that there can be only one main() function in the entire program since it's the entry point of the program. When you compile both files into object files and link them, the linker will find two main() functions and report an error.

Here’s what will happen:

  1. Compilation (with -c):
    When you run gcc -c main.c -o main.o and gcc -c mymem.c -o mymem.o, both files will compile successfully, producing main.o and mymem.o respectively. The reason it doesn't fail at this step is that the compilation phase doesn't care about multiple main() definitions; it only generates individual object files.

  2. Linking (with gcc main.o mymem.o -o main.run):
    During the linking stage, GCC will try to combine the object files (main.o and mymem.o) into a single executable. At this point, it will find two main() function definitions and will give an error like this:

    vbnet
    /usr/bin/ld: multiple definition of `main'; mymem.o:(.text+0x0): first defined here /usr/bin/ld: main.o:(.text+0x0): multiple definition of `main' collect2: error: ld returned 1 exit status

Solution:

To resolve this, ensure that only one file (in your case, main.c) contains the main() function, and the other file (mymem.c) contains other functions or logic but no main() function.

If you want to test mymem.c separately and temporarily have a main() function in it, you can:

  • Remove or comment out the main() in mymem.c before compiling your final program.
  • Alternatively, rename or isolate the main() function in mymem.c for testing purposes (e.g., renaming it to test_main()).

But when you're ready to compile everything together, there should only be one main() function in the entire project.

Comments

Popular posts from this blog

Ubuntu Notes: Set up autossh as systemd useful-reminder commands

 sudo vim /etc/systemd/system/permanentAutossh.service ======================================== [Unit] Description=Keeps a tunnel to myOciFreeNat open After=network-online.target [Service] User=<username> Environment="AUTOSSH_GATETIME=0" ExecStart=/usr/bin/autossh -M 0 -q -N -o "ServerAliveInterval 60" -o "ServerAliveCountMax 3" -L 4322:127.0.0.1:5432 -i /<ssh_private_key_file_absolute_path> <username>@<ip_address> -p 22 [Install] WantedBy=multi-user.target ======================================== sudo systemctl daemon-reload sudo systemctl enable permanentAutossh sudo systemctl start permanentAutossh ================== sudo systemctl daemon-reload sudo systemctl restart permanentAutossh sudo systemctl status permanentAutossh ====================== sudo systemctl stop permanentAutossh sudo systemctl disable permanentAutossh sudo rm /etc/systemd/system/permanentAutossh.service

syslog cpp programming: learning using chatGcp

  Introduction to Syslog C++ August 27, 2024 This conversation may reflect the link creator’s personalized data, which isn’t shared and can meaningfully change how the model responds. You said: I am new to syslog in cpp programming n just starting. Can you teach me ChatGPT said: ChatGPT Sure! syslog is a standard for logging system messages in Unix-like operating systems. It provides a way to send log messages to the system log, which can then be collected and analyzed by various tools. Here's a basic guide to get you started with syslog in C++: 1. Include the Necessary Header To use syslog , you need to include the syslog.h header: cpp Copy code # include <syslog.h> 2. Open the Connection to syslog Before sending log messages, you need to open a connection to the syslog system. This is typically done at the start of your program: cpp Copy code openlog ( "your_program_name" , LOG_PID | LOG_CONS, LOG_USER); "your_program_name" : A string representing ...

Ubuntu - C++ Notes: Install & update boost c++ library from git (may contain some error in process mentioned below)

 Boost C++ Library Installation from git in ubuntu: 1. create a directory named boost in your desired location and go to that directory mkdir boost;cd boost; 2. clone boost recursively from git using command git clone --recursive https://github.com/boostorg/boost.git 3. cd boost; sudo ./bootstrap.sh; 4. sudo ./b2; 5. sudo ./b2 install; DONE! --------------------------- Boost C++ Library Update Verson from git in Ubuntu: 1. go to gitDownloads/boost directory cd gitDownloads/boost; 2. git pull; 3. git submodule update --recursive; 4. cd boost; sudo ./bootstrap.sh; 5. sudo ./b2; 6. sudo ./b2 install; DONE!