Re: [RFC] block: Change the granularity of io ticks from ms to ns

[Jens Axboe]

On 12/6/22 11:15?AM, Gulam Mohamed wrote:
> Use ktime to change the granularity of IO accounting in block layer from
> milli-seconds to nano-seconds to get the proper latency values for the
> devices whose latency is in micro-seconds. After changing the granularity
> to nano-seconds the iostat command, which was showing incorrect values for
> %util, is now showing correct values.
> 
> We did not work on the patch to drop the logic for
> STAT_PRECISE_TIMESTAMPS yet. Will do it if this patch is ok.
> 
> The iostat command was run after starting the fio with following command
> on an NVME disk. For the same fio command, the iostat %util was showing
> ~100% for the disks whose latencies are in the range of microseconds.
> With the kernel changes (granularity to nano-seconds), the %util was
> showing correct values. Following are the details of the test and their
> output:

As mentioned, this will most likely have a substantial performance
impact. I'd test it, but your patch is nowhere near applying to the
current block tree. Please resend it against for-6.2/block so it can
get tested.

-- 
Jens Axboe