[squid-users] Survey on assertions: When the impossible happens

Alex Rousskov rousskov at measurement-factory.com
Mon Feb 29 16:43:09 UTC 2016


On 02/29/2016 03:44 AM, Eray Aslan wrote:
> On Sat, Feb 27, 2016 at 10:56:53AM -0700, Alex Rousskov wrote:
>> Q0: Do you think an admin should be able to control the choice among the
>> three options detailed above?

> Not really, no.  But if you think it is not an undue burden for
> developers, why not?

>> Q1: Which option is the best default?
> 
> Option 1 - bail out.


>> Q2: Would you prefer to see fewer assertions in exchange for more memory
>> leaks and an increased probability of malformed/corrupted/misleading
>> HTTP messages?

> Nope.  I'd be worried that it would result in more fragile and harder to
> debug systems.  I shouldn't have to babysit my servers.

Thanks a lot for sharing your preferences!

Perhaps the context of those questions was somehow missed/lost in the
noise I have created around them. Sorry. Let me rephrase the last
question to illustrate why "I shouldn't have to babysit my servers",
while obviously true, implies the opposite of what you seem to be
suggesting:

Q2: Your Squid is asserting every 5 minutes. There is no [working] Squid
version you can switch to. Your network topology does not allow you to
bypass Squid. Until the bug is fixed, would you prefer to see fewer
assertions in exchange for more memory leaks and an increased
probability of malformed/corrupted/misleading HTTP messages?


Thank you,

Alex.



More information about the squid-users mailing list