The tag has no usage guidance.

learn more… | top users | synonyms (1)

0
votes
0answers
7 views

How to mmap file w/ HUGE_PAGES to specific memory location (via “memmap=4G$4G”)

Presently working: Device driver to mmap to specific memory location (isolated by boot parameter "memmap=4G$4G") via the remap_pfn_range call. Desired solution: Same/similar outcome using 2M pages ...
3
votes
1answer
23 views

How does Linux manage “simultaneous” writes to swap/disk partitions in virtual memory?

I'm currently working on an educational operating system called Pintos. While implementing virtual memory, one of the issues that I'm having is writing data to swap in a page fault that happened while ...
1
vote
0answers
14 views

What is the on-demand mapping in the kernel virtual memory in Linux? [duplicate]

In the OS lecture, the lecturer explained that not all the physical memory will fit into virtual address space on a 32-bit architecture. So what the kernel can do is map anything else above 896MB ...
0
votes
0answers
20 views

Why does .text region of shared libraries is not flagged as VM_SHARED?

When I'm using shmem/mmap to share memory between processes I can see with pmap that it creates virtual memory area that marked as shared. Example: Address Kbytes RSS Dirty Mode ...
0
votes
0answers
10 views

How do I write to a __user memory from within the top half of an interrupt handler? [migrated]

I am working on a proprietary device driver. The driver is implemented as a kernel module. This module is then coupled with an user-space process. It is essential that each time the device generates ...
1
vote
1answer
26 views

vmstat -s command fields meaning, specially “pages paged in” vs “pages swapped in”

Most of the fields are understandable but can someone please explain me the difference between "pages paged in" and "pages swapped in"?. I'm pretty sure that swapping is when the entire process is ...
1
vote
0answers
39 views

Does Linux maintain a system RAM high water mark?

I know there is VmHWM entry in each process's /proc/[PID]/status file, however is there an aggregate of this that contains the high water mark for the system? I understand the free command give the ...
3
votes
2answers
85 views

C++ app. with mmap kills kernel? (kernel panic with mmap)

In my C++ program where intensive disk, network I/O and even CPU computation occur, I am using memory mapped region as an array. With very small data, it works fine. However when I ran the program ...
1
vote
0answers
45 views

Transparent Huge Pages, Pagetable size and /proc/<pid>/status

TL;DR; My pagetable is far bigger than it should be when using transparent huge pages (THP). I have a program (see below), that allocates 50 GiB of memory, requests transparent huge pages and faults ...
1
vote
1answer
53 views

Why deleting big files from tmpfs is not instantaneous?

$ cat /proc/mounts | egrep ' /tmp ' tmpfs /tmp tmpfs rw,nosuid,nodev,relatime 0 0 $ dd if=/dev/zero bs=1M count=3000 of=/tmp/q 3000+0 records in 3000+0 records out 3145728000 bytes (3.1 GB) copied, ...
1
vote
0answers
14 views

FORTRAN executables: heap maxed out

I am trying to run a FORTRAN program on stampede (xsede machine). The error message I am getting is 'heap maxed out'. I think it has something to do with virtual memory allocation. So I use the ...
0
votes
1answer
43 views

Downsides of processes with high virtual size but low RAM and GPU memory use

I have noticed that some of my processes take a lot of virtual size in my computer. I understand that the virtual size of a process is the sum of memory it is actually using, memory it has mapped into ...
3
votes
1answer
95 views

FDT relocated by U-Boot cannot be accessed by Linux (in highmem)

We run a customized version of U-Boot on an ARM-based embedded system and would like to load Linux 4.3 with a device tree blob. The system features 1GB of RAM of which the top 128MB are reserved for ...
1
vote
0answers
50 views

Linux kernel running only with use of physical address

Is it theoretically possible to make Linux which for its own kernel (include modules) uses only physical addresses? (it means it completely omits MMU) For processes how would you know if there was ...
-1
votes
1answer
53 views

What is page fault and when does it occur? [closed]

In an interview I was asked this question: what is a page fault and when does it happen?
0
votes
2answers
29 views

prevent from writing to a large continuous section of virtual memory [closed]

How can an operating system kernel efficiently prevent a user process from writing to a large continuous section of virtual memory?
1
vote
0answers
15 views

How does an OS detect an access to random memory address of a compiled program? [duplicate]

I've read a couple things about memory management/virtual memory and I need a little more details on one important point. If I compile a program and it does an access to a hard-coded address without ...
3
votes
1answer
373 views

Accessing Memory Mapped I/O is slow

I have a Terasic-SoCKIT(fpga & arm cortex a9) and I have Linux running on the HPS. I'm trying to access the memory mapped I/O, wrote a simple character driver with functions "request_mem_region" ...
0
votes
0answers
32 views

How do I find corresponding kernel virtual addresses and userspace virtual addresses for a coreboot table driver?

How does kernel virtual addresses relate to userspace virtual addresses and is there a way to map the two with a kernel function? Some background: Coreboot puts some information in a table structure ...
2
votes
0answers
55 views

What does it mean when a private VM page is none of `rwx`?

UPDATE: It's a padding: every such non-rwx area is preceded with a readable and/or writable area and together they constitute a 64Mb segment (for 64bit architecture). A relevant question on SO: ...
7
votes
1answer
1k views

How do I increase the maximum swap space on Mac OS X? [closed]

On Mac OS X Yosemite 10.10.5, when I try to run a calculation that needs to allocate and use 128 GB of memory (it is a command line program written in C), the kernel kills my process with extreme ...
0
votes
0answers
82 views

Where can I find the MMU,CR3 and TLB for creating virtual addresses?

I want to understand virtual addressing and read many times the terms: MMU TLB (Translation Lookaside Buffer) and CR3 But currently I'm a bit confused. My confusion is: MMUThe MMU is hardware. ...
2
votes
0answers
54 views

When waiting on a pagefault, in what kind of sleep is a task?

Are tasks put into interruptible/uninterruptible/killable sleep when waiting on a pagefault? Does it matter, what kind of pagefault is it?
2
votes
2answers
114 views

Shared library load mem address region is architecture dependent?

I see that on x86, in a process's VM, shared libraries are loaded between heap and stack, i.e. the mmap area as noted in most of the online articles. But on a PowerPC linux box, I see that all ...
1
vote
2answers
161 views

On page fault, how does Unix determine if the faulting address is in swap space?

When a page fault occurs for a virtual address for any process how does the linux/unix operating system determine whether that page (of that virtual address) was swapped previously present in memory ...
4
votes
1answer
234 views

Shared library mappings in /proc/pid/maps

Why does /proc/pid/maps contain a few records for the same library ? Here is an example: 7fae7db9f000-7fae7dc8f000 r-xp 00000000 08:05 536861 ...
1
vote
0answers
42 views

Print kernel memory layout

Userland memory layout can be inspected by looking into /proc/self/maps. I am wondering if there is a similar facility allowing to inspect runtime kernel memory layout?
3
votes
2answers
294 views

Physical Address Extension - how do virtual addresses work?

I'm running Debian Linux. uname -m says i686 which means 32-bit architecture machine with pae flag enabled. getconf LONG_BIT is 32. Installed RAM capacity is 6GB. My /proc/cpuinfo has an entry ...
3
votes
1answer
302 views

Kernel address space layout

Userland address space is well documented, which includes segments like heap, stack, .text, .bss, etc. But there is not enough documentation on kernel address space. Since certain virtual address is ...
1
vote
0answers
57 views

Why process is killed while a lot of memory is free?

I am running a python script in ipython. This script will take about 8GB RAM. The system has more than 80 GB free RAM but the swap is nearly 0. My script was killed after it runned for a while. I want ...
5
votes
0answers
118 views

How do I vmtouch a directory (not the files it contains)?

The vmtouch(8) tool allows locking a file or files in memory. It has recursive mode, but the directories are used just for discovering files and are not locked themselves. How do I lock a directory ...
1
vote
1answer
111 views

Why does my process take too long to die?

Basically I'm using Linux 2.6.34 on PowerPC (Freescale e500mc). I have a process (a kind of Virtual Machine that was developed in-house) that uses about 2.25 G of mlocked VM. When I kill it, I notice ...
0
votes
0answers
94 views

Is High Virtual Memory usage a problem or may cause problems?

In our server, we have a python based code that listen ports. The amount of Virtual Memory it uses is increased greatly with time Like: USER PID %CPU %MEM VSZ RSS TTY STAT ...
3
votes
1answer
134 views

How do I forbid access to physical memory in Linux?

I'm on an embedded system (Zynq from Xilinx. It uses ARMv7, Cortex-A9), and running Linux. I need to ensure that no access to a certain physical memory range is ever made, either accidentally by the ...
0
votes
0answers
30 views

Page Fault Frequency Algorithm - Compute number of frames and mean resident set

I'm reading about Page Fault Frequency algorithm but I don't understand how can I compute the number of frames. For example I have my reference string: 112233444412412214432255543 and control ...
1
vote
1answer
104 views

Case study of virtual memory management

Need help in understanding virtual memory concept. When a process requesting for 2GB mapping onto the virutal memory in Linux environment of 4GB ( 1GB Kernel : 3GB Userspace), when already another ...
0
votes
0answers
46 views

fast way to find the address range from the given info

I have a question, If I am given some memory devices with size specifications, how do i map it to address range quickly. if the address space is of 32 GB. Ex: ROM - 1Mb 3 RAMs - 2 GB each 2 FLASH - ...
1
vote
1answer
231 views

Is the Linux kernel affected by paging?

Is the whole kernel always loaded to RAM whatever the size of the RAM? In other words, can the Linux kernel be affected by paging (some part of kernel reside in virtual memory)?
2
votes
2answers
126 views

How to get the virtual storage size of a process continuously?

We all know that top command monitors the running processes continuously. I have an application that is running continuously in an embedded Linux and I need to monitor its VSZ (Virtual storage size) ...
0
votes
1answer
133 views

/dev/mapper/vg00-var maxing out

Over the past few years we have had multiple Linux servers have the same problem time and time again: our /dev/mapper/vg00-var folder maxes out at 100%, which means all sites on the server die. We ...
10
votes
1answer
277 views

Does anyone actually use and benefit from transparent huge pages?

I've been struggling with transparent huge pages performance issues of late, and noticed many database systems recommend turning it off. I am talking Oracle, Postgresql, MySQL, Cassandra, NuoDB, ...
2
votes
0answers
70 views

JVM low-memory tuning

What command-line options would provide the lowest memory-footprint JVM, in OpenJDK, or possibly other JVMs (Linux/Debian)? I'm willing to disable JIT, live with slow or choppy garbage collection, ...
1
vote
0answers
66 views

In the Linux Kernel what file/process controls the assignment of permissions to memory pages?

A given memory page may be writable, readable or executable. What kernal source code file in the linux kernal describes the setting of these rights? What process or kernal data structure would set the ...
-1
votes
2answers
659 views

Generate major page faults

Is it possible to generate major page faults in the linux kernel at will? Can a program be written such that it is guaranteed to cause a major page fault on it's execution.
1
vote
1answer
119 views

Linux always hangs when out of physical memory

I'm using ArchLinux, with 3.18.6-1 kernel, when a software uses more than physical memory (when total memory used is >5.8 GB), it always lags, unresponsive, and all that I can do is reset the ...
2
votes
0answers
83 views

How can I let high priority processes continue when low priority processes are causing free memory to be low

Ok I'm not sure if this is the correct place to post this. It is more of a 'why not' question than a 'how to' one (assumption is that it isn't/can't be done). Why don't we allow RAM to be partitioned ...
0
votes
2answers
150 views

Are the size of a memory page and the size of a file system cluster always the same?

From http://en.wikipedia.org/wiki/Page_%28computer_memory%29 A page, memory page, or virtual page is a fixed-length contiguous block of virtual memory, described by a single entry in the page ...
5
votes
1answer
328 views

When does swap start to be used? When does a process get an out of memory error and be killed?

When does swap start to be used? Is it when the memory is fully used? Or when the memory hasn't been fully used? When does a process get an "Out of memory" error and be killed by the kernel? is it ...
3
votes
0answers
376 views

Why does saving a KVM-QEMU VM requires additional memory?

I have three VMs running on Red Hat Enterprise Linux with 8 GB RAM, each of the VMs has 3 GB allocated, and I also run a 512 MB VM. If we also consider the guest OS's memory usage (usually 1.5 GB due ...
2
votes
0answers
582 views

Xorg consuming 1.1GB, is it a leak?

I am facing a problem wherein Xorg starts to consume more and more memory and finally eats up the whole swap space. As shown below, Xorg's virtual memory is about 1.1GB. My system runs only one GTK ...