On 11.03.2015 16:32, stan wrote: > On Wed, 11 Mar 2015 13:32:09 +0100 > poma <pomidorabelisima@xxxxxxxxx> wrote: > >>> 1. You still haven't provided basic information about the processor, >> thus 'lscpu' or a similar command. > $ lscpu > Architecture: x86_64 > CPU op-mode(s): 32-bit, 64-bit > Byte Order: Little Endian > CPU(s): 6 > On-line CPU(s) list: 0-5 > Thread(s) per core: 2 > Core(s) per socket: 3 > Socket(s): 1 > NUMA node(s): 1 > Vendor ID: AuthenticAMD > CPU family: 21 > Model: 2 > Model name: AMD FX(tm)-6300 Six-Core Processor > Stepping: 0 > CPU MHz: 3500.000 > CPU max MHz: 3500.0000 > CPU min MHz: 1400.0000 > BogoMIPS: 7023.57 > Virtualization: AMD-V > L1d cache: 16K > L1i cache: 64K > L2 cache: 2048K > L3 cache: 8192K > NUMA node0 CPU(s): 0-5 > >> >> 2. Moreover you still haven't provided the difference between >> "I'm running Fedora 21 with a custom compiled kernel, >> 3.19.0-1.20150211.fc21.x86_64." and stock Fedora kernel - >> 3.18.8-201.fc21.x86_64, i.e. >> diff /boot/config-3.18.8-201.fc21.x86_64 /boot/3.19.0-1.20150211.fc21.x86_64 >> > I can do this but I think it is too large for a message. > There are 1532 lines of output from that command. > >> 3. Also you haven't mentioned whether the same happens with the stock >> Fedora kernel. > > Yes, it did. > >> >> 4. And you haven't explained why you use a custom kernel, and why >> particularly 3.19 kernel. > > To remove all the generalizations that have to be in stock kernels so > they can work for everyone. It greatly speeds compilation to not do > all those drivers that I don't need. Sound cards I don't have > > Latest that created packages without errors. I'll be upgrading to 4.0 > kernel shortly. https://bugzilla.redhat.com/show_bug.cgi?id=1199312 > >> >> 5. Etc. >> >> How anybody can help in this way, man. >> > > I don't see how those have any relevance. All the answers to them > would do is be noise or distraction. This is at a meta level above > that, about the design and control level, rather than the implementation > details. I guess I am assuming that the kernel programmers have done > their job, and the kernel functionality is abstracted from the > underlying hardware. Especially for x86 architectures. > > I think Heinz has put his finger on the issue in his response: a single > process is limited to a single core. But, if that single process can > spawn other processes, which is what 'make -j6' should be doing, why > would that be true? I'll be following up in my response to him. > > Thanks for taking an interest, and I'm not trying to be hostile, but I > honestly don't see how answering your questions helps. > The Devil is in the detail. Both: 1. diff -u /boot/config-3.18.8-201.fc21.x86_64 /boot/config-3.19.0-1.20150211.fc21.x86_64 2. dmidecode (as root) to http://fpaste.org s'il vous plaît. -- users mailing list users@xxxxxxxxxxxxxxxxxxxxxxx To unsubscribe or change subscription options: https://admin.fedoraproject.org/mailman/listinfo/users Fedora Code of Conduct: http://fedoraproject.org/code-of-conduct Guidelines: http://fedoraproject.org/wiki/Mailing_list_guidelines Have a question? Ask away: http://ask.fedoraproject.org
