https://github.com/memcached/memcached/blob/master/doc/new_lru.txt

On Wed, 21 Jun 2017, red 888 wrote:

> Ah thanks that must be what he's talking about. Can you recommend a good in 
> depth doc on the LRU tail (that includes info about the hot,warm,cold tails)?
> Thanks again!
> On Tuesday, June 20, 2017 at 8:06:17 PM UTC-4, Dormando wrote:
>       I don't really understand what queue tail is. I didn't write that page.
>
>       There's the LRU tail. Which just means the least recently used item for
>       that slab class.
>
>       On Tue, 20 Jun 2017, red 888 wrote:
>
>       > Just curious about what the queue tail is and where I can get more 
> info about it and what it does.
>       >
>       > On Jun 20, 2017 5:25 PM, "dormando" <[email protected]> wrote:
>       >       On Tue, 20 Jun 2017, red 888 wrote:
>       >
>       >       > This doc says something about memcached I haven't read 
> anywhere else:
>       >       > Which brings me to another point, items/chunks are not 
> actively reclaimed/expired.
>       >       Memached does not
>       >       > have a background thread that explicitly expires items, 
> reclaiming used chunks for new
>       >       items. When a
>       >       > slab needs a chunk and there are no more pages, Memcache will 
> look at the queue tail
>       >       for items to
>       >       > evict. Memcache will make a best effort to evict expired 
> items (items you've explicitly
>       >       set to expire
>       >       > after some time). In scenario 1, item 2, an expired item, is 
> evicted. However, in
>       >       scenario 2, item 1,
>       >       > which has not yet expired, will be evicted, even though item 
> 4 would seem like the
>       >       better candidate.
>       >       > But since item 4 is not near the tail, Memcached stops 
> looking and just expires item 1.
>       >       >
>       >       > So what is the memcache queue tail and why can't I find much 
> info about it? Seems
>       >       pretty important
>       >       > because what he is saying is that memcache could evict a non 
> expired item, if it ran
>       >       out of
>       >       > unassigned pages, had plenty of expire items for the slab 
> classes, but because an
>       >       expired was nearer
>       >       > the "tail" (whatever that means) it evicted that one instead.
>       >
>       >       What is the problem you're trying to solve?
>       >
>       >       If you run the latest version and start it with "-o modern" 
> option,
>       >       there's an LRU crawler that will reap expired items in the 
> background.
>       >
>       >       --
>       >
>       >       ---
>       >       You received this message because you are subscribed to a topic 
> in the Google Groups
>       >       "memcached" group.
>       >       To unsubscribe from this topic, visit
>       >       
> https://groups.google.com/d/topic/memcached/liqaRhhYi3A/unsubscribe.
>       >       To unsubscribe from this group and all its topics, send an 
> email to
>       >       [email protected].
>       >       For more options, visit https://groups.google.com/d/optout.
>       >
>       > --
>       >
>       > ---
>       > You received this message because you are subscribed to the Google 
> Groups "memcached" group.
>       > To unsubscribe from this group and stop receiving emails from it, 
> send an email to
>       > [email protected].
>       > For more options, visit https://groups.google.com/d/optout.
>       >
>       >
>
> --
>
> ---
> You received this message because you are subscribed to the Google Groups 
> "memcached" group.
> To unsubscribe from this group and stop receiving emails from it, send an 
> email to [email protected].
> For more options, visit https://groups.google.com/d/optout.
>
>

-- 

--- 
You received this message because you are subscribed to the Google Groups 
"memcached" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to