dont-use-fsync real world impact

[Niall O'Reilly]

On 28 Sep 2019, at 12:33, Jure Sah wrote:

> I see, so if theoretically the DHCP server could work in such a way as
> to "fsync asynchronously" (oxymoron I know), in that the lease could be
> written to disk before it is offered to the client, but not necessarily
> before the next lease could be served, then this would adhere to the
> RFC, represent no real performance penalty, while also not limiting the
> rate at which requests can be served.
>
> What changes would be required for this to work?

Have you read the documentation for the delayed-ack and max-ack-delay
statements?

> [...]
>
> I am just trying to find a solution to this problem that is infinitely
> scalable.

To echo Steinar Haug, neither the network nor the client population is
infinitely scalable.

IMHO, it makes sense to have infrastructure scale in proportion to
demand, and to use monitoring to identify both when there is insufficient
headroom and where the real choke-points are.

The most significant bottleneck to DHCP services which I ever had to deal
with was due to excessive fsync in the syslog process, not even in dhcpd.

Niall O'Reilly