On Fri, Mar 26, 2010 at 12:08:48PM +0100, Amon Ott wrote: > I can confirm this problem on our test system. glusterfs goes up to the memory > limit set for performance/io-cache (1.2 GB here), logs out of memory errors > and further access fails with "Stale NFS file handle". The above command did > not help, only remounting did. > > So I assume some memory leak in the io-cache filter. No, this should happen without any filters. What happens, if you disable io-cache? > > > Have a look at patchsets which are soon going to come soon, which enable us > > to pin point the leaks here: > > > > http://patches.gluster.com/ > > http://patches.gluster.com/patch/2971/ <- patchset starts here > > > > With 3.1 we will have more clear answer fo all memory related questions. > > Do I have to scrape all related patches out of that server by hand to test it? > I assume they are not yet production ready. Get them, recompile and try out, but rather on a test filesystem. Krzysztof
