Messages in this thread | | | Date | Mon, 22 Aug 2005 13:52:08 -0700 | From | tony.luck@intel ... | Subject | Re: CONFIG_PRINTK_TIME woes |
| |
>> we go there ... I'd like to hear whether there are usage models that >> really need better resolution than jiffies can provide? > >I think so. Say you're debugging or performance tuning filesystem requests >and I/O completions, etc. You disable the console with `dmesg -n', run the >test then do `dmesg -s 1000000 > foo'. Having somewhat-sub-millisecond >timestamping in the resulting trace is required.
That sounds like using a hammer to pound in screws ... it works, but it might be a lot better to go find a screwdriver.
Couldn't you use kprobes to collect timestamps of interesting events in your filesystem instead of splashing printk() all over the place?
But perhaps this is heresy, real kernel programmers do all their debugging with printk() :-)
-Tony - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |