Tag Info

New answers tagged


You could simple add your own tracing rules (by using unused tcp port, for sample): for table in $(</proc/net/ip_tables_names);do while read dsc nam foo ;do if [ "$dsc" == "Chain" ];then iptables -t $table -I $nam -p tcp --dport 8 -j LOG --log-prefix "start-${table}-${nam} " iptables -t $table -A $nam -p tcp --dport 8 ...


I found the issue here. I needed to look at /proc/meminfo and see what the the kernel was caching as slab space. My problem was not understanding how much "free" memory top/ps/free said I had. It was the fact that these numbers were not adding up. The "free" command would tell me I had roughly 1692mb free but my processes only totaled up to about 20% of my ...


You have about 1692m in free memory according to Linux. In the top "Mem" line it would seem like your memory is almost 99% (7793m / 7840m) but in reality you're only using about 78% of available memory. See also http://www.linuxatemyram.com/ for a more in-depth explanation. Free vs Top vs /proc/meminfo Process memory. Adding up the memory used by ...


I believe you are misreading the Buffers/Cache - there is > 6 gigs being used as memory cache as per the +/- Buffers/Cache line. If this is needed it can be eaten into - as its not, the OS is using it to cache disk reads and similar.


Honestly the request sounds a bit suspicious to me. Can't you just move things and see what load is like on the new system? That being said, onto your actual issue. You need to find out the resource usage of processes (and not the whole system). Option 1: You can actually launch the processes with some sort of profiler or tracing tool (i.e. perf and ...


ps_mem.py is IMO bit more precise because it assesses amount of shared memory correct where top is buggy. top reads /proc/<PID>/statm whereas ps_mem.py reads more detailed info from /proc/<PID>/smaps and assesses total usage of multi-processing daemon with more precision. For details I recommend reading through ps_mem.py code

Top 50 recent answers are included