On Wed, 12 Oct 2011 15:26:31 -0600, Alex Rousskov wrote:
> SMP shared memory cache stats were not collected.
>
> Mean disk object size stats were aggregated inaccurately for SMP.
>
> Moved Store-related stats into a dedicated StoreStats class,
> encapsulating memory cache-related (mem), disk cache-related (swap),
> and
> global store (number of objects) stats. Used consistent naming scheme
> to
> make memory and disk stats more alike (we could create a class to
> represent "store device" stats of sorts, but that seems like an
> overkill
> at this time).
>
> Moved Store stats collection into corresponding Store classes rather
> than forcing GetInfo() in stat.cc to know how to deal with all Store
> stats.
>
>
> The new code seems to work in my very limited tests but I am pretty
> sure
> more stats/SMP-related fixes will be needed.
>
>
> I would also like to polish mgr:info display of Store stats along the
> same mem/disk symmetry lines, remove duplicated, and add missing
> information there, but I am worried that changing mgr:info output
> format
> will break old scripts. Perhaps we should add a new mgr:store action
> instead?
Within reason we have free-reign over changes to cache mgr reports. The
scripts I'm aware of all seem to scan for particular lines and parse
their content if present.
Can you mock-up what the changed output would look like please?
Amos
Received on Wed Oct 12 2011 - 22:25:23 MDT
This archive was generated by hypermail 2.2.0 : Thu Oct 13 2011 - 12:00:11 MDT