Re: many lost ticks, clock drifts problems also with debian smp kernel?
Selon Andrew Sharp <[EMAIL PROTECTED]>: > Define extended period of time. My definition for "extended period of heavy load" would be: >From 2 days up to 2 weeks of Integer/floating point computation with both cores maxed out, all 4 Gigs of RAM used up, 10 Gigs of swap allowed, log files of several Gigs incrementally written on a 500 Go RAID0 array, plus heavy network load. Usually the clock drift starts to be really noticeable after a few hours, a week after the machine still runs and computes the clock is 4 months off, you can't log into the machine because all passwd timers time out before you can even move your finger ! By the way the 2.6.14.3 kernel seems to have cured the problem for me, but now my promise IDE controller and my built in ethernet card don't work anymore... -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
Re: Re: many lost ticks, clock drifts problems also with debian smp kernel?
Hi mike, as a linux newbie there are some terms I don't get quite well > This is a kernel problem with SMP having unsynced TSC's running at what is a TSC? > different freqs, supposedly fixed in kernel 2.6.14. Before 2.6.14 i > needed to boot with pci=noacpi and clock=pmtmr to solve the 'lost > 'ticks'. what does the clock=pmtmr bootparam do? > A Debian kernel won't change anything. assuming you have a similar config > (e.g. HPET_TIMER=y PM_TIMER=y). You may want to post this on the LKML. what is HPET_TIMER=y ? what is PM_TIMER=y ? and what is LKML? Thanks -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]
many lost ticks, clock drifts problems also with debian smp kernel?
Hi, I have a machine with an AMD64 x2 4800+ mounted on an asus A8V Deluxe. I have experienced massive clock drift problems with smp kernels from the fedora core 4 x86_64 distribution, also with the newer 2.6.14.3 kernel from kernel.org: -- dmesg : Losing some ticks... checking if CPU frequency changed. warning: many lost ticks. Your time source seems to be instable or some driver is hogging interupts rip 0x435036 --- I have tried the pci=routeirq, acpi=off, noapic, nolapic, no_timer_check, no_tsc... bootparams without any real succes, my system clock keeps on drifting away faster and faster after the system has been up for some time. My question to the list is : Are the debian amd64-k8-smp kernels also subject to this problem? I have browsed the entirety of the 2005 amd64 lists and have found various posts about clock problems, but they were all laptop related, with the non smp kernel. So far I haven't found any debian user reporting the same problme I face now, but who knows, I'd like to make this sure before I break my current fedora install and start a rather time consuming debian install (time consuming because I have never used debian before). Thanks for your help, /rémi -- To UNSUBSCRIBE, email to [EMAIL PROTECTED] with a subject of "unsubscribe". Trouble? Contact [EMAIL PROTECTED]