Re: [PATCH] migration/calc-dirty-rate: millisecond precision period

[Peter Xu]

On Thu, Jun 29, 2023 at 11:59:03AM +0300, Andrei Gudkov wrote:
> Introduces alternative argument calc-time-ms, which is the
> the same as calc-time but accepts millisecond value.
> Millisecond precision allows to make predictions whether
> migration will succeed or not. To do this, calculate dirty
> rate with calc-time-ms set to max allowed downtime, convert
> measured rate into volume of dirtied memory, and divide by
> network throughput. If the value is lower than max allowed
> downtime, then migration will converge.
> 
> Measurement results for single thread randomly writing to
> a 24GiB region:
> +--------------+--------------------+
> | calc-time-ms | dirty-rate (MiB/s) |
> +--------------+--------------------+
> |          100 |               1880 |
> |          200 |               1340 |
> |          300 |               1120 |
> |          400 |               1030 |
> |          500 |                868 |
> |          750 |                720 |
> |         1000 |                636 |
> |         1500 |                498 |
> |         2000 |                423 |
> +--------------+--------------------+
> 
> Signed-off-by: Andrei Gudkov <gudkov.andrei@huawei.com>

Andrei, do you plan to enhance the commit message and data in a repost?  I
assume you may want to have your data points updated after the discussion,
and it won't need to be in a rush as it will only land 8.2.

The patch itself looks fine to me:

Acked-by: Peter Xu <peterx@redhat.com>

Thanks,

-- 
Peter Xu