Re: Multiple storeio types?

Henrik Nordstrom wrote:

> Probably missing from the round-robin directory selection. Should be trivial
> to add.

Yep. It was. Patch will be forthcoming when I've tested it.

 
> Suggestion: Take a short break and figure our how you want to have the usage
> balanced when you mix different store types. Then get it implemented and send
> us a patch.

Quick query regarding the least load and UFS type. Is there a reason
for choosing constant 999 for the loadav for that store type? I mean is
it magic in some way that I'm not seeing? Could it just as easily be,
say, 500? That's not a real fix, of course. A real fix doesn't look
trivial (hence the reason it's returning a constant I guess ;-), as I
don't see any way to gather the load that is sensible. But 500 might be
more fair when used with other storedir types, and would behave the same
  as it currently does if all dirs are ufs type.

Another query, that is somewhat related: Are the diskd and aufs loadav
calculations 'compatible'? I guess it would take test data that
probably doesn't exist yet to know since they both rely on somewhat
arbitrary load indicators and both behave very differently based on
those conditions.

If I find that least load is more efficient for my needs, I'm going to
give a diskd storedir type a try on my RAM disk. Maybe lighter weight
than 16 threads... Any thoughts on whether I'm misled in that assumption?

Thanks for the tips, guys!

> On Thursday 08 November 2001 13.40, Joe Cooper wrote:
>
>>Oops. I lied.
>>
>>Now it ignores max-size.
>>
>>Joe Cooper wrote:
>>
>>>You're quite right. Switching to round-robin fixes the issue.
>>>
>>>Thanks Andres!
>>>
>>>Andres Kroonmaa wrote:
>>>
>>>> I think its to do with load-based selection algoritm.
>>>> ufs is reported with constant load of 99.9% while aufs has variable
>>>> load based on queue length and no of dirs. aufs always wins, and
>>>> ufs isn't even considered.
>>>> Try switch to roundrobin dir selection algoritm.
>>>>
>>>> See storeDirSelect* in src/store_dir.c.
>>>> Imho this is a bug, although not sure how to handle this.
>>>>
>
>

-- 
Joe Cooper <joe@swelltech.com>
http://www.swelltech.com
Web Caching Appliances and Support