[lkml]   [1999]   [Mar]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
    SubjectRe: [patch] recover losed timer interrupt using the TSC [Re: [patch] kstat change to see how much Linux SMP really scale well]
    On Tue, 16 Mar 1999, Ulrich Windl wrote:

    >> + register unsigned long delta_usec;
    >> +
    >> + __asm__("mull %2"
    >> + :"=a" (delta_cycles), "=d" (delta_usec)
    >> + :"g" (fast_gettimeoffset_quotient), "0" (delta_cycles));
    >> + delta_usec -= delay_usec;
    >> + delta_usec /= 1000000/HZ;
    >Your delta_usec is in fact a lost_ticks. The name is confusing when
    >you add microseconds to jiffies. (IMHO)

    Ok, agreed. It was not a problem right now but removing the `_usec' could
    be a better choice. Thanks.

    >> -long tick = (1000000 + HZ/2) / HZ; /* timer interrupt period */
    >> +long tick = 1000000 / HZ; /* timer interrupt period */
    >This way the system time will be more behind than before if
    >"(1000000 % HZ) >= HZ/2". IMHO the line is correct. After all we are
    >not saying "(1000000 + HZ - 1) / HZ".

    ;). Agreed. I also needed such trick that to make the recover of the lost
    ticks completly relialable. I just removed such changes from my second
    patch. But thanks for commenting about that. I wanted to hear if I was
    missing something of more serious or it was only an attempt to decrease
    the error in integer divisions.

    Andrea Arcangeli

    To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
    the body of a message to
    Please read the FAQ at

     \ /
      Last update: 2005-03-22 13:50    [W:0.019 / U:4.188 seconds]
    ©2003-2017 Jasper Spaans. hosted at Digital OceanAdvertise on this site