How much do we care about high-load scenarios?

John D. Bell JDB at systemsartisans.com
Wed Sep 14 18:42:48 UTC 2016


Current professional systems administrator (former professional programmer)
here.  I hope I am adding light and not merely heat to this discussion.

quoting Eric -

> The underlying point is that blade and rack servers are cheap.  Cycles
> are cheap.  This gives the option of implicitly saying to operators
> "high-load conditions are *your* problem - fix it by rehosting your
> NTP" rather than doing what I think would be premature optimization
> for the high-load case.  If we jump right in and implement threading
> we *are* going to pay for it in increased future defect rates.

More servers are not cheap *everywhere*.  Most of the medium-to-large scale
machine rooms I am familiar with are rather crowded.  Combine that with
the cooling, power, and physical setup (racking, cabling, etc.) costs, and
many
site administrators would rather try to load another 'small' service onto an
existing server.  Also, fewer servers means less staff work.

On the other hand, I sympathize with the compelling case of not wanting to
complicate the code more than is absolutely necessary.  *If* I were the
architect on this project (thankfully I'm not!) I would get the code
simplified
and streamlined in single-thread mode as far as possible, and then design
and code a POSIX-threading-conformant "improvement".



  - *John D. Bell*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.ntpsec.org/pipermail/devel/attachments/20160914/4ab03ea6/attachment.html>


More information about the devel mailing list