TDB historical performance (with pretty graphs)

tridge at tridge at
Fri Jun 19 01:50:54 GMT 2009

Hi Rusty,

 >     I've been doing some measurements on tdb performance, mainly to see if all 
 > the additions since the old code (eg. transactions, hasnfn) have caused 
 > noticeable slowdown.  Was a bit of a pain to compile all the versions (git 
 > didn't seem to figure out all those source moves), and so some are missing, but 
 > I was interested in trends.

yes, there is some noise, but it's nice to see that it hasn't been
slowly degrading over time like so much software does :-)

 > we seem to suck recently on the "replace 5000 4byte key 4 byte date
 > records with 8 byte dataa records"

That is indeed a puzzle. If I'm reading it right, then we slowed down
by 4x between git 77dab7 and 8c8820 for the 4 byte to 8 byte expand. 

I can't see anything in the code history that could explain
that. Maybe you could re-check that one manually?

Cheers, Tridge

More information about the samba-technical mailing list