Re: Proposed change to make cancellations safe

On 24 April 2016 at 17:54, Shay Rojansky <roji(at)roji(dot)org> wrote:

> I definitely agree that simply tracking message sequence numbers on both
> sides is better. It's also a powerful feature to be able to cancel all
> messages "up to N" - I'm thinking of a scenario where, for example, many
> simple queries are sent and the whole process needs to be cancelled.
>

For security, I think any non-matching cancellation would be ignored so
that only someone with proper context could issue the cancel.

Issuing bulk cancellations sounds like a bad plan.

Yes, this has been happening to some Npgsql users, it's not very frequent
> but it does happen from time to time. I also bumped into this in some
> automated testing scenarios. It's not the highest-value feature, but it is
> an improvement to have if you plan on working on a new protocol version.
>
> Let me know if you'd like me to update the TODO.
>

If you've got an itch, expecting someone else to scratch it is less likely
to succeed.

--
Simon Riggs http://www.2ndQuadrant.com/
<http://www.2ndquadrant.com/>
PostgreSQL Development, 24x7 Support, Remote DBA, Training & Services