Re: Query regarding size-16384 cache in kernel

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



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


[Index of Archives]     [Newbies FAQ]     [Linux Kernel Mentors]     [Linux Kernel Development]     [IETF Annouce]     [Git]     [Networking]     [Security]     [Bugtraq]     [Yosemite]     [MIPS Linux]     [ARM Linux]     [Linux RAID]     [Linux SCSI]     [Linux ACPI]
  Powered by Linux