[WBEL-users] Re: Hyperthreading not enabled in WB kernels?
Johnny Hughes
mailing-lists@hughesjr.com
Thu, 29 Apr 2004 06:02:42 -0500
--=-0yR51dOCxR2kYipkPimE
Content-Type: text/plain
Content-Transfer-Encoding: 7bit
On Wed, 2004-04-28 at 23:49, Vincent.Raffensberger@dtn.com wrote:
> That's interesting. I looked into my old messages from the initial
> install and found the same thing, so it's probably not the kernel
> version.
> I have a couple of these boxes, so I'll swap the disk into another one
> and see what happens. It may just be an issue with that particular
> system.
> What does your /proc/cpuinfo say?
>
> Thanks.
I also have a dual xeon processor box with hyperthreading and it show
all 4 cpus (when using the cat /proc/cpuinfo and dmesg). Here is the
output of dmesg | grep -i cpu:
# dmesg | grep -i cpu
..... CPU clock speed is 2796.9558 MHz.
cpu: 0, clocks: 998307, slice: 199661
CPU0<T0:998304,T1:798640,D:3,S:199661,C:998307>
cpu: 1, clocks: 998307, slice: 199661
cpu: 2, clocks: 998307, slice: 199661
cpu: 3, clocks: 998307, slice: 199661
CPU1<T0:998304,T1:598976,D:6,S:199661,C:998307>
CPU2<T0:998304,T1:399312,D:9,S:199661,C:998307>
CPU3<T0:998304,T1:199648,D:12,S:199661,C:998307>
cpu_sibling_map[0] = 2
cpu_sibling_map[1] = 3
cpu_sibling_map[2] = 0
cpu_sibling_map[3] = 1
mapping CPU#0's runqueue to CPU#2's runqueue.
mapping CPU#1's runqueue to CPU#3's runqueue.
Starting migration thread for cpu 0
Starting migration thread for cpu 1
Starting migration thread for cpu 2
Starting migration thread for cpu 3
-Johnny Hughes
--=-0yR51dOCxR2kYipkPimE
Content-Type: text/html; charset=utf-8
Content-Transfer-Encoding: 7bit
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 TRANSITIONAL//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; CHARSET=UTF-8">
<META NAME="GENERATOR" CONTENT="GtkHTML/3.0.9">
</HEAD>
<BODY>
On Wed, 2004-04-28 at 23:49, Vincent.Raffensberger@dtn.com wrote:
<BLOCKQUOTE TYPE=CITE>
<FONT COLOR="#737373" SIZE="2"><I>That's interesting. I looked into my old messages from the initial install and found the same thing, so it's probably not the kernel version.<BR>
I have a couple of these boxes, so I'll swap the disk into another one and see what happens. It may just be an issue with that particular system.<BR>
What does your /proc/cpuinfo say?</FONT><BR>
<FONT COLOR="#737373"></FONT><BR>
<FONT COLOR="#737373" SIZE="2">Thanks.</I></FONT>
</BLOCKQUOTE>
<BR>
I also have a dual xeon processor box with hyperthreading and it show all 4 cpus (when using the <B>cat /proc/cpuinfo </B>and <B>dmesg</B>). Here is the output of <B>dmesg | grep -i cpu</B>:<BR>
<BR>
<B># dmesg | grep -i cpu<BR>
</B><BR>
..... CPU clock speed is 2796.9558 MHz.<BR>
cpu: 0, clocks: 998307, slice: 199661<BR>
CPU0<T0:998304,T1:798640,D:3,S:199661,C:998307><BR>
cpu: 1, clocks: 998307, slice: 199661<BR>
cpu: 2, clocks: 998307, slice: 199661<BR>
cpu: 3, clocks: 998307, slice: 199661<BR>
CPU1<T0:998304,T1:598976,D:6,S:199661,C:998307><BR>
CPU2<T0:998304,T1:399312,D:9,S:199661,C:998307><BR>
CPU3<T0:998304,T1:199648,D:12,S:199661,C:998307><BR>
cpu_sibling_map[0] = 2<BR>
cpu_sibling_map[1] = 3<BR>
cpu_sibling_map[2] = 0<BR>
cpu_sibling_map[3] = 1<BR>
mapping CPU#0's runqueue to CPU#2's runqueue.<BR>
mapping CPU#1's runqueue to CPU#3's runqueue.<BR>
Starting migration thread for cpu 0<BR>
Starting migration thread for cpu 1<BR>
Starting migration thread for cpu 2<BR>
Starting migration thread for cpu 3<BR>
<BR>
-Johnny Hughes<BR>
<BR>
<BR>
<BR>
</BODY>
</HTML>
--=-0yR51dOCxR2kYipkPimE--