[Monetdb-developers] GooglePerformanceTools with MonetDB?
GooglePerformanceTools gives an alternative (threaded) implementation of malloc under a BSD License. Has it even been tested with MonetDB before? http://code.google.com/p/google-perftools/wiki/GooglePerformanceTools I mean, it looks very simple to use and test :) And implements the ideas I have heard before by doing memory management with big chunks of memory instead of small allocations. Stefan
On 04-08-2009 19:53:12 +0200, Stefan de Konink wrote:
GooglePerformanceTools gives an alternative (threaded) implementation of malloc under a BSD License. Has it even been tested with MonetDB before?
http://code.google.com/p/google-perftools/wiki/GooglePerformanceTools
I mean, it looks very simple to use and test :) And implements the ideas I have heard before by doing memory management with big chunks of memory instead of small allocations.
from a previous life I recall that it was said to be boosting MySQL, but actually setting it up wasn't as trivial as it seemed
On Tue, 4 Aug 2009, Fabian Groffen wrote:
from a previous life I recall that it was said to be boosting MySQL, but actually setting it up wasn't as trivial as it seemed
Someone asked if I could do a comparison on my favorite webserver; If it is as trivial as it looks, I'll see if I can come up with a compile patch for MonetDB. I mean if someone wants to run on a TPC-H scalefactor N that probably will give some more insights :) Stefan
Furthermore, most malloced structures in MAL are all recycled cheaply. Fabian Groffen wrote:
On 04-08-2009 19:53:12 +0200, Stefan de Konink wrote:
GooglePerformanceTools gives an alternative (threaded) implementation of malloc under a BSD License. Has it even been tested with MonetDB before?
http://code.google.com/p/google-perftools/wiki/GooglePerformanceTools
I mean, it looks very simple to use and test :) And implements the ideas I have heard before by doing memory management with big chunks of memory instead of small allocations.
from a previous life I recall that it was said to be boosting MySQL, but actually setting it up wasn't as trivial as it seemed
------------------------------------------------------------------------------ Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day trial. Simplify your report design, integration and deployment - and focus on what you do best, core application coding. Discover what's new with Crystal Reports now. http://p.sf.net/sfu/bobj-july _______________________________________________ Monetdb-developers mailing list Monetdb-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/monetdb-developers
Chunk based (m)allocation of structures was part of MonetDB version 1. Stefan de Konink wrote:
GooglePerformanceTools gives an alternative (threaded) implementation of malloc under a BSD License. Has it even been tested with MonetDB before?
http://code.google.com/p/google-perftools/wiki/GooglePerformanceTools
I mean, it looks very simple to use and test :) And implements the ideas I have heard before by doing memory management with big chunks of memory instead of small allocations.
Stefan
------------------------------------------------------------------------------ Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day trial. Simplify your report design, integration and deployment - and focus on what you do best, core application coding. Discover what's new with Crystal Reports now. http://p.sf.net/sfu/bobj-july _______________________________________________ Monetdb-developers mailing list Monetdb-developers@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/monetdb-developers
participants (3)
-
Fabian Groffen -
Martin Kersten -
Stefan de Konink