Tag Info

New answers tagged

0

I expect you have a DUAL CORE Pentium 4 and this enables you to run 64bit code. The earlier single processor P4s ran at a lower speed and only worked 32bit.


0

The load average does not just cover processes using CPU time or waiting for it. It also covers those processes in uninterruptable sleep (which usually means waiting for disk I/O). Dividing by the number of CPUs would lead to some bizarre (and often useless) numbers. If you have a system with 4 cores and 7 processes waiting for a single disk, the load ...


-1

you should use the command mdiag -n to check whether the nodes are idle or busy.


1

You didn't say but I'm assuming this is for Linux. Even though you are looking for the historical reason for it being per CPU, your question indicates that you are still thinking of the load average in terms of CPU utilization instead of the kernel job queue that it really is. You can still see CPU utilization in programs like top if you want to see a % ...


0

Do you mean all processes started by some process (have the same parent PID)? If you have pgrep you can filter all the processes with the same parent ID: top -p $(pgrep -P 2069 -d,) If not you can filter all process ids through awk and use them with top -p: top -p $(ps -eo pid,ppid |awk '($2==2069){printf "%s%s",delim,$1; delim=","}') Change $2==2069 ...


0

You could isolate some cpu cores from kernel scheduling using isolcpus parameter. Add this parameter to your grub.conf and reboot to take effect. You can find more info and example at http://nairobi-embedded.org/cpu_affinity.html#the-isolcpus-kernel-parameter


4

You haven't found any reliable answer because there is no widely applicable reliable answer. The performance gain from multiple cores is hard to predict except for well-defined tasks, and even then it can depend on many other factors such as available memory (no benefit from multiple cores if they're all waiting for some file to load). For ordinary desktop ...


1

Some operations in GIMP will take advantage of multiple cores; others don't, but this is an active area of development and should be expected to improve over time if you keep your version of GIMP up to date.


3

Many applications aren't explicitly multi-threaded, so their CPU-bound tasks will indeed be limited to one core at a time. Modern web browsers, however, use (at least) one core per window, so if you have multiple windows open you'll benefit from multiple cores. More importantly, running Linux systems consists of many processes running, all taking turns ...


0

Did you try the man pages? Both cgconfig.conf(5) and cgrules.conf(5) have nice examples, it shouldn't be difficult modifying those to match your needs. You will probably want to start from something like (be warned I have not tested it): In /etc/cgrules.conf: root:sshd * sshdcg/ * * default/ and ...


1

Unfortunately even different portions of the same build may be optimal with conflicting j factor values, depending on what's being built, how, which of the system resources are the bottleneck at that time, what else is happening on the build machine, what's going on in the network (if using distributed build techniques), status/location/performance of the ...


5

nproc gives the number of CPU cores/threads available, e.g. 8 on a quad-core CPU supporting two-way SMT. The number of jobs you can run in parallel with make using the -j option depends on a number of factors: the amount of available memory the amount of memory used by each make job the extent to which make jobs are I/O- or CPU-bound make -j$(nproc) is ...


2

You want some processor affinity (or CPU affinity). The relevant syscall is sched_setaffinity(2), but you should use it thru pthread_set_affinity_np(3) if you want to code your benchmarks for that. The related command is taskset(1) and you might use it on the commands you want to benchmark (or on your shell). If possible, take care that the machine is ...


0

In your case %idle is the 11th column. To see all the rows where the idle percentage is below 100 you can use: mpstat 1 |awk '$11<100' If you are only interested in the value of the idle percentage column you can use: mpstat 1 |awk '$11<100{print $11}'


2

If you are only interested in the memory used after the fact, then use GNU time: command time -v myprogram (the above uses the bash way of invoking the external time command rather than the bash builtin, your shell may vary). Or, GNU memusage: memusage -T ./myprogram If you are interested in the memory used on an ongoing basis (i.e. during a long ...


3

It would depend on what kind of stats you want, but if you're writing a program in C running on Linux, you'd definitely better know about Valgrind. Valgrind can, not only profile detailed memory usage of your program, but also detect memory access violations which are common in C and possibly very hard to debug. For your profiling purpose, take a look at ...


1

Here's the resident set size and virtual memory size of all sshd processes on one system: ulric@qvp2:~$ ps -eo rss,vsz,args|grep sshd|grep -v grep 448 55292 /usr/sbin/sshd -D 5176 147460 sshd: ulric [priv] 2776 149704 sshd: ulric@pts/3 Or perhaps easier: ulric@qvp2:~$ ps aux|head -n 1&&ps aux|grep sshd|grep -v grep USER PID %CPU %MEM ...



Top 50 recent answers are included