Fong Vang wrote:
I have a total of 20 CentOS 4.1 systems running on fairly new hardware. About 6 of them are experiencing strange hangs without any indication -- nothing in /var/log/messages nor on the console -- sometime within 10-30 minutes after a reboot. The systems still responds to ping but you can't ssh to it. At the console, you could type "root" at the user prompt but it hangs immediately after hitting enter.
Memory scan of all systems show no error.
Any idea how to troubleshoot this problem. The system's not responsive to do any troubleshooting and nothing abnormal is in the log.
We running htis kernel: kernel-smp-2.6.9-11.EL.i686.rpm.
Have you tried disabling hyperthreading? I had suffered this problem when we started buying Intel Xeon's, disabling HT'ing seemed to fix the problem for me.
Dean
On 1/19/06, Plant, Dean dean.plant@roke.co.uk wrote:
Fong Vang wrote:
I have a total of 20 CentOS 4.1 systems running on fairly new hardware. About 6 of them are experiencing strange hangs without any indication -- nothing in /var/log/messages nor on the console -- sometime within 10-30 minutes after a reboot. The systems still responds to ping but you can't ssh to it. At the console, you could type "root" at the user prompt but it hangs immediately after hitting enter.
Memory scan of all systems show no error.
Any idea how to troubleshoot this problem. The system's not responsive to do any troubleshooting and nothing abnormal is in the log.
We running htis kernel: kernel-smp-2.6.9-11.EL.i686.rpm.
Have you tried disabling hyperthreading? I had suffered this problem when we started buying Intel Xeon's, disabling HT'ing seemed to fix the problem for me.
Some people suggested that too. I'm asking for two of these systems to be sent back from our remote data center. I'll try it then.
Did you just ended up running without hyperthreading? Did you ever find a solution? It seems an awful waste if you can't use it.
Dean _______________________________________________ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
On Thu, 19 Jan 2006, Fong Vang wrote:
Did you just ended up running without hyperthreading? Did you ever find a solution? It seems an awful waste if you can't use it.
I'd have a hard time calling a performance hit of no more than 10% to 15% (and typically much less than that) an "awful waste." :-)
On Thu, 2006-01-19 at 09:11 -0800, Paul Heinlein wrote:
On Thu, 19 Jan 2006, Fong Vang wrote:
Did you just ended up running without hyperthreading? Did you ever find a solution? It seems an awful waste if you can't use it.
I'd have a hard time calling a performance hit of no more than 10% to 15% (and typically much less than that) an "awful waste." :-)
exactly ... hyperthreading is mostly "hype" ... and very little "rthreading" :)
Thursday, January 19, 2006, 10:14:54 AM, you wrote:
On Thu, 2006-01-19 at 09:11 -0800, Paul Heinlein wrote:
On Thu, 19 Jan 2006, Fong Vang wrote:
Did you just ended up running without hyperthreading? Did you ever find a solution? It seems an awful waste if you can't use it.
I'd have a hard time calling a performance hit of no more than 10% to 15% (and typically much less than that) an "awful waste." :-)
exactly ... hyperthreading is mostly "hype" ... and very little "rthreading" :)
I've heard a lot of criticism on hyperthreading on various lists. While I haven't actually measured the performance of a machine that has it enabled vs. disabled, I have noticed that the same machine with hyperthreading enabled responds much faster to SSH logins etc. when the machine is under heavy loads. Given that I've had no problems with using HT, I'm happy to have it.
On Thu, 2006-01-19 at 11:22 -0800, Mickael Maddison wrote:
Thursday, January 19, 2006, 10:14:54 AM, you wrote:
On Thu, 2006-01-19 at 09:11 -0800, Paul Heinlein wrote:
On Thu, 19 Jan 2006, Fong Vang wrote:
Did you just ended up running without hyperthreading? Did you ever find a solution? It seems an awful waste if you can't use it.
I'd have a hard time calling a performance hit of no more than 10% to 15% (and typically much less than that) an "awful waste." :-)
exactly ... hyperthreading is mostly "hype" ... and very little "rthreading" :)
I've heard a lot of criticism on hyperthreading on various lists. While I haven't actually measured the performance of a machine that has it enabled vs. disabled, I have noticed that the same machine with hyperthreading enabled responds much faster to SSH logins etc. when the machine is under heavy loads. Given that I've had no problems with using HT, I'm happy to have it.
Absolutely, if it works on given hardware then use it, any performance gain is worth having :)
But if you look objectively at the gain, it is not 2x the performance ... maybe 1.25x ... maybe a little more ... maybe not.
If it is broken, it is not the end of the world though, which I think was the initial point.
It is not nearly as much an increase in performance as you see with dual core processors, for example.
I've heard a lot of criticism on hyperthreading on various lists. While I haven't actually measured the performance of a machine that has it enabled vs. disabled, I have noticed that the same machine with hyperthreading enabled responds much faster to SSH logins etc. when the machine is under heavy loads. Given that I've had no problems with using HT, I'm happy to have it.
Absolutely, if it works on given hardware then use it, any performance gain is worth having :)
But if you look objectively at the gain, it is not 2x the performance ... maybe 1.25x ... maybe a little more ... maybe not.
My experience is pretty much the same, the increase in performance varies - usually around 10-30% (depends on how well optimized programs are), but it greatly improves responsiveness (the simple fact that when one program is using up all of the cpu there is still that 20% left for other tasks - and 20% of 2GHz CPU is still quite a decent amount of horsepower)...
Cheers, MaZe.
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1
On Thu, Jan 19, 2006 at 09:11:59AM -0800, Paul Heinlein wrote:
On Thu, 19 Jan 2006, Fong Vang wrote:
Did you just ended up running without hyperthreading? Did you ever find a solution? It seems an awful waste if you can't use it.
I'd have a hard time calling a performance hit of no more than 10% to 15% (and typically much less than that) an "awful waste." :-)
Not to mention something disabling HT will actually improve performance.
- -- Rodrigo Barbosa rodrigob@suespammers.org "Quid quid Latine dictum sit, altum viditur" "Be excellent to each other ..." - Bill & Ted (Wyld Stallyns)
-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1
On Thu, Jan 19, 2006 at 08:57:41AM -0800, Fong Vang wrote:
On 1/19/06, Plant, Dean dean.plant@roke.co.uk wrote:
Fong Vang wrote:
I have a total of 20 CentOS 4.1 systems running on fairly new hardware. About 6 of them are experiencing strange hangs without any indication -- nothing in /var/log/messages nor on the console -- sometime within 10-30 minutes after a reboot. The systems still responds to ping but you can't ssh to it. At the console, you could type "root" at the user prompt but it hangs immediately after hitting enter.
Memory scan of all systems show no error.
Any idea how to troubleshoot this problem. The system's not responsive to do any troubleshooting and nothing abnormal is in the log.
We running htis kernel: kernel-smp-2.6.9-11.EL.i686.rpm.
Have you tried disabling hyperthreading? I had suffered this problem when we started buying Intel Xeon's, disabling HT'ing seemed to fix the problem for me.
Some people suggested that too. I'm asking for two of these systems to be sent back from our remote data center. I'll try it then.
Did you just ended up running without hyperthreading? Did you ever find a solution? It seems an awful waste if you can't use it.
Disabling HT only solves it on single processor systems.
- -- Rodrigo Barbosa rodrigob@suespammers.org "Quid quid Latine dictum sit, altum viditur" "Be excellent to each other ..." - Bill & Ted (Wyld Stallyns)
-
Fong Vang -
Johnny Hughes -
Maciej Żenczykowski -
Mickael Maddison -
Paul Heinlein -
Plant, Dean -
Rodrigo Barbosa