diff options
| author | Eric Dumazet | 2012-04-03 07:28:28 +0200 |
|---|---|---|
| committer | David S. Miller | 2012-04-03 22:43:18 +0200 |
| commit | eb6a24816b247c0be6b2e97e68933072874bbe54 (patch) | |
| tree | c815981e955e9e32d1b9bd279bd18a358038e031 /crypto/aead.c | |
| parent | net: Report dev->promiscuity in netlink reports. (diff) | |
| download | kernel-qcow2-linux-eb6a24816b247c0be6b2e97e68933072874bbe54.tar.gz kernel-qcow2-linux-eb6a24816b247c0be6b2e97e68933072874bbe54.tar.xz kernel-qcow2-linux-eb6a24816b247c0be6b2e97e68933072874bbe54.zip | |
af_unix: reduce high order page allocations
unix_dgram_sendmsg() currently builds linear skbs, and this can stress
page allocator with high order page allocations. When memory gets
fragmented, this can eventually fail.
We can try to use order-2 allocations for skb head (SKB_MAX_ALLOC) plus
up to 16 page fragments to lower pressure on buddy allocator.
This patch has no effect on messages of less than 16064 bytes.
(on 64bit arches with PAGE_SIZE=4096)
For bigger messages (from 16065 to 81600 bytes), this patch brings
reliability at the expense of performance penalty because of extra pages
allocations.
netperf -t DG_STREAM -T 0,2 -- -m 16064 -s 200000
->4086040 Messages / 10s
netperf -t DG_STREAM -T 0,2 -- -m 16068 -s 200000
->3901747 Messages / 10s
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'crypto/aead.c')
0 files changed, 0 insertions, 0 deletions