Messages in this thread | | | Subject | Re: /proc/stat btime accuracy problem | From | john stultz <> | Date | Wed, 01 Jun 2011 17:49:05 -0700 |
| |
On Wed, 2011-06-01 at 18:31 -0600, Bjorn Helgaas wrote: > On Wed, Jun 1, 2011 at 5:58 PM, john stultz <johnstul@us.ibm.com> wrote: > > My first instinct is "don't do that!" to whatever driver is disabling > > irqs for so long. Do you know what's actually causing these long irq off > > periods? > > > > I assume you're noticing this offset by seeing that CLOCK_REALTIME is > > off from the RTC right after boot? How severe is this? The RTC read is > > only second granular, so there's a fair amount of error (~1 second) > > possible right at boot, so this then must be many seconds worth of lost > > ticks to be noticeable, right? > > I'm using 2.6.34, so not really new. I think the major offender is > kernel serial printk, which is done in polled mode. A *lot* of it, > e.g., 30+ seconds' worth.
CC'ing the linux-serial list and Alan for their thoughts: Does the serial port is disabling irqs for 30+ seconds during boot seem at all sane?
I would think it would periodically enable irqs in the polling loop to let things be processed, but maybe not?
> I wonder if there's some reasonably clean > way to resync with the RTC, say at the time we register a clocksource > better than jiffies, or in clocksource_done_booting(), or something.
I definitely think we need to address the long irq disable periods instead of trying to hack around the issue in the timekeeping code.
thanks -john
| |