Hi Sowmya, On Tue, Jan 18, 2011 at 6:06 AM, Sowmya Sridharan <sowmya.sridharan@xxxxxxx> wrote: > > Hi, > > We see an continuous increase in slab size of 1GB for slab cache named > "size-16384" in a system. > The system is stable and sending/receiving bulk amounts of packets. > > "/proc/slabinfo" Initial Value: > size-16384(DMA) 0 0 16384 1 4 : tunables 8 4 0 : slabdata 0 0 0 > size-16384 9247 9247 16384 1 4 : tunables 8 4 0 : slabdata 9247 9247 0 > > "/proc/slabinfo" Final Value: > size-16384(DMA) 0 0 16384 1 4 : tunables 8 4 0 : slabdata 0 0 0 > size-16384 75023 75023 16384 1 4 : tunables 8 4 0 : slabdata 75023 75023 0 > > Can anyone please tell us what kind of functions in kernel need to allocate > an object for "size-16384"? Doing kmalloc( 9000, GFP_KERNEL) will allocate a size-16384 object. Typically doing any allocation in the range 8193 throuh 16384 will allocate a 16k object. You'll probably need to enable something like kmemleak in order to track down who is doing the allocations. <http://lxr.linux.no/linux+v2.6.37/Documentation/kmemleak.txt> > In what possible scenarios are these slab objects allocated? Once you find the leak, you'll probably know the answer. Dave Hylands _______________________________________________ Kernelnewbies mailing list Kernelnewbies@xxxxxxxxxxxxxxxxx http://lists.kernelnewbies.org/mailman/listinfo/kernelnewbies
