Revision 1519e57fe81c14bb8fa4855579f19264d1ef63b4 authored by Francois Romieu on 03 February 2011, 11:02:36 UTC, committed by Francois Romieu on 04 February 2011, 09:38:10 UTC
Some experiment-based action to prevent my 8168 chipsets locking-up hard
in the irq handler under load (pktgen ~1Mpps). Apparently a reset is not
always mandatory (is it at all ?).

- RTL_GIGA_MAC_VER_12
- RTL_GIGA_MAC_VER_25
  Missed ~55% packets. Note:
  - this is an old SiS 965L motherboard
  - the 8168 chipset emits (lots of) control frames towards the sender

- RTL_GIGA_MAC_VER_26
  The chipset does not go into a frenzy of mac control pause when it
  crashes yet but it can still be crashed. It needs more work.

Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Cc: Ivan Vecera <ivecera@redhat.com>
Cc: Hayes <hayeswang@realtek.com>
1 parent b5ba6d1
History
File Mode Size
Kconfig -rw-r--r-- 3.0 KB
Makefile -rw-r--r-- 431 bytes
acl.h -rw-r--r-- 2.4 KB
auth.c -rw-r--r-- 2.0 KB
auth.h -rw-r--r-- 540 bytes
cache.h -rw-r--r-- 1.6 KB
export.c -rw-r--r-- 38.8 KB
idmap.h -rw-r--r-- 2.3 KB
lockd.c -rw-r--r-- 1.7 KB
nfs2acl.c -rw-r--r-- 8.6 KB
nfs3acl.c -rw-r--r-- 6.3 KB
nfs3proc.c -rw-r--r-- 24.5 KB
nfs3xdr.c -rw-r--r-- 26.6 KB
nfs4acl.c -rw-r--r-- 21.5 KB
nfs4callback.c -rw-r--r-- 25.5 KB
nfs4idmap.c -rw-r--r-- 13.3 KB
nfs4proc.c -rw-r--r-- 38.0 KB
nfs4recover.c -rw-r--r-- 9.3 KB
nfs4state.c -rw-r--r-- 115.0 KB
nfs4xdr.c -rw-r--r-- 84.0 KB
nfscache.c -rw-r--r-- 7.6 KB
nfsctl.c -rw-r--r-- 37.9 KB
nfsd.h -rw-r--r-- 14.0 KB
nfsfh.c -rw-r--r-- 18.3 KB
nfsfh.h -rw-r--r-- 4.2 KB
nfsproc.c -rw-r--r-- 20.1 KB
nfssvc.c -rw-r--r-- 15.6 KB
nfsxdr.c -rw-r--r-- 13.0 KB
state.h -rw-r--r-- 15.8 KB
stats.c -rw-r--r-- 2.7 KB
vfs.c -rw-r--r-- 52.9 KB
vfs.h -rw-r--r-- 4.0 KB
xdr.h -rw-r--r-- 4.0 KB
xdr3.h -rw-r--r-- 7.9 KB
xdr4.h -rw-r--r-- 16.9 KB

back to top