Thanks
On Thu, Apr 25, 2019, 10:04 Larry Brigman <[email protected]> wrote: > Dmidecode will give you much about the hardware/firmware on the machine. > > On Thu, Apr 25, 2019, 8:47 AM VY <[email protected]> wrote: > > > Thanks for your reply. > > The reason I highlighted this field is exactly what you brought up -- > this > > number is different in the other > > machines I have in our data center. All the others say "4" but this one > > machine is "25". > > Not sure how I can look up firmware or whether specter mitigation has > been > > applied. Need to look those up. > > > > thanks > > > > > > On Wed, Apr 24, 2019 at 7:36 PM Ben Koenig <[email protected]> wrote: > > > > > On 4/24/19 5:40 PM, VY wrote: > > > > Dear All > > > > > > > > I need some help with reading the output of /proc/cpuinfo. > > > > > > > > We have several machines and they are all supposedly identical Intel > > Xeon > > > > machines. 4 CPUs each and identical Linux version. > > > > One of the machines are reporting VERY high load consistently. > > > > They are all running identical applications and I don't see any > > > difference > > > > in load. > > > > > > > > However, when I look at /proc/cpuinfo, this "very high load" box is > > > saying: > > > > > > > > apicid : 25 > > > > > > > > initial apicid : 25 > > > > > > > > > > > > > > > > All the other machines are reporting 4 for this number. > > > > > > > > Does it matter what this number say? I looked online but cannot > quite > > > tell > > > > whether it matters or not. > > > > > > > > > > > > > > > > thanks > > > > > > > > > > > > -v > > > > _______________________________________________ > > > > PLUG mailing list > > > > [email protected] > > > > http://lists.pdxlinux.org/mailman/listinfo/plug > > > > > > > > > the apicid might be unrelated to what you are troubleshooting. My > > > understanding is that it's an identifier used to keep track of logical > > > cores. > > > > > > If this number is the same on all your other systems then all that says > > > is that this CPU might be from a different lot. > > > > > > It could also suggest a difference in microcode, or BIOS firmware, > which > > > you can identify through more effective means. > > > > > > > > > I would compare some of the other details, such as the various levels > of > > > firmware that govern software->hardware interactions. Maybe this box is > > > running a different spectre mitigation? > > > > > > > > > _______________________________________________ > > > PLUG mailing list > > > [email protected] > > > http://lists.pdxlinux.org/mailman/listinfo/plug > > > > > _______________________________________________ > > PLUG mailing list > > [email protected] > > http://lists.pdxlinux.org/mailman/listinfo/plug > > > _______________________________________________ > PLUG mailing list > [email protected] > http://lists.pdxlinux.org/mailman/listinfo/plug > _______________________________________________ PLUG mailing list [email protected] http://lists.pdxlinux.org/mailman/listinfo/plug
