hello, I've a simple AFR configure, two server, two client. if I do copy of 10G file, glusterfs client process grows and grows , > 5Go however I just define volume io-cache type performance/io-cache option cache-size 2048MB # default is 32MB option page-size 128KB #128KB is default option option cache-timeout 2 # default is 1 subvolumes iothreads end-volume so it is glibc problem or a memory leak ? memory does not scale down. Nicolas On Fri, Mar 20, 2009 at 11:35 AM, Gordan Bobic <gordan@xxxxxxxxxx> wrote: > On Thu, 19 Mar 2009 12:43:20 -0700, Amar Tumballi <amar@xxxxxxxxxxx> wrote: >>> >>> Thanks for the update, I'll try it tonight. Any news on the memory leak? >>> Have you managed to track it down yet? >>> >> >> We noticed that its some issue with 'arena algorithm' of glibc's memory >> management. We are working on solving this issue properly. Should have an >> update soon. As of now, there is no 'leak' observed, but all of the > issues >> were related to memory fragmentation problems. > > Interesting. I can't quite see how memory fragmentation could be > responsible for such extreme memory usage growth that eventually uses up > all RAM+swap, but I'll be happy to test this when I manage to get rc5 to > boot. > > Gordan > > > _______________________________________________ > Gluster-devel mailing list > Gluster-devel@xxxxxxxxxx > http://lists.nongnu.org/mailman/listinfo/gluster-devel >
