storing in db  2.51020598412  for  24438  tweets
storing in memcached  1.89508605003
reading from db  8.4804828167
reading from memcached  0.249507188797


Now this is awesome :D


On Aug 18, 2:04 pm, Neeraj Agarwal <[email protected]> wrote:
> storing in db  2.22120189667  for  24438  tweets
> storing in memcached  1.91712522507
> reading from db  7.59235692024 (multi-get)
> reading from memcached  1.85763192177 (single get)
>
> With libmemcached :)
>
> much improvement :D
>
> On Aug 18, 12:31 pm, dormando <[email protected]> wrote:
>
>
>
>
>
>
>
> > You should go read the manuals.
>
> > Look for "multiget" or mget or get_multi or whatever functions. I don't
> > know what the equivalent set routines would look like for pylibmemc
> > offhand. It should be in the documentation.
>
> > If not, and someone knows, they should pipe up :)
>
> > -Dormando
>
> > On Thu, 18 Aug 2011, Neeraj Agarwal wrote:
> > > I have pasted my code above.
>
> > > I tried my program again by writing back the results in a file.
> > > perhaps mongo just pushes the request and returns so it wasn't taking
> > > much time while memcached is a blocking call.
>
> > > storing in db  1.26978802681  for  11437  tweets
> > > storing in memcached  1.5911450386
> > > reading from db  41.3619318008                           (was reading
> > > one record at a time from db and writing it to the file)
> > > reading from memcached  1.78016901016            (similarly with
> > > memcached)
>
> > > mongodb still winning in terms of writing..
>
> > > Does libmemcached groups multiple get/ set calls? Or are they even
> > > blocking calls?
>
> > > Thanks for your time,
> > > Neeraj
>
> > > On Aug 18, 12:08�pm, dormando <[email protected]> wrote:
> > > > > 85 seconds was because of the network latency (was using EC2 with my
> > > > > computer. pinging time was 350 ms itself..)
>
> > > > > Perhaps for x many number of items, it was taking x*350 ms time for
> > > > > making calls.. while mongo, it was sending all data at one go.
>
> > > > > So I ran the script on the server itself:
> > > > > storing in db �0.108298063278 �for �1487 �items
> > > > > storing in memcached �0.208426952362
> > > > > reading from db �0.0738799571991
> > > > > reading from memcached �0.145488023758
>
> > > > > what am I doing wrong here?
>
> > > > Can you attach your benchmark program?
>
> > > > You should be using multiget to fetch back items quicker. Try using
> > > > pylibmc, which is based off of libmemcached. That may be able to do
> > > > multisets and get you better speed. The other library is pure python, I
> > > > think. Would be slower than a native DB driver.
>
> > > > -Dormando

Reply via email to