From: | Simon Riggs <simon(at)2ndQuadrant(dot)com> |
---|---|
To: | Shay Rojansky <roji(at)roji(dot)org> |
Cc: | Tom Lane <tgl(at)sss(dot)pgh(dot)pa(dot)us>, PostgreSQL-development <pgsql-hackers(at)postgresql(dot)org> |
Subject: | Re: Proposed change to make cancellations safe |
Date: | 2016-04-24 21:14:13 |
Message-ID: | CANP8+j+V98kCp-X+bYpZGt7X3=OCKouqKfDcZArnCk6S4wf3Gw@mail.gmail.com |
Views: | Raw Message | Whole Thread | Download mbox | Resend email |
Thread: | |
Lists: | pgsql-hackers |
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
From | Date | Subject | |
---|---|---|---|
Next Message | Tom Lane | 2016-04-24 21:38:38 | Re: Proposed change to make cancellations safe |
Previous Message | Simon Riggs | 2016-04-24 21:10:19 | Re: Suspicious behaviour on applying XLOG_HEAP2_VISIBLE. |