Re: About the "temperature histogram" of tier-agent

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi MingXin, Li,

Does the below make sense to you?

Thanks!
sage


On Tue, 28 Nov 2017, YuFan Chen wrote:

> Hi,
> 
>    Before Jewel, the code uses "atime" to distinguish hot/cold data:
> 
>           agent_estimate_atime_temp() calculates the distance.
>           It means colder data gets longer distance (larger value)
> 
> 
>    In Jewel, it changes to use temperature with weight.
>             So, colder data gets smaller value.
> 
>     However, it still use the "old semantics" to determine evicting or not in
>            ReplicatedPG::agent_estimate_atime_temp();
> 
>     if (1000000 - temp_upper >= agent_state->evict_effort)
>        return false;
> 
> 
>      if there is no misunderstanding, should it change to that:
> 
> --- a/src/osd/ReplicatedPG.cc
> +++ b/src/osd/ReplicatedPG.cc
> @@ -12211,7 +12211,7 @@ bool
> ReplicatedPG::agent_maybe_evict(ObjectContextRef& obc, bool
> after_flush)
>      delete f;
>      *_dout << dendl;
> 
> -    if (1000000 - temp_upper >= agent_state->evict_effort)
> +    if (temp_upper >= agent_state->evict_effort)
>        return false;
>    }
> 
> Yu Fan
> --
> To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
> 
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html



[Index of Archives]     [CEPH Users]     [Ceph Large]     [Information on CEPH]     [Linux BTRFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]
  Powered by Linux