diff options
| author |   John Fastabend <john.r.fastabend@intel.com> | 2011-08-23 03:14:22 +0000 |
|---|---|---|
| committer |   Jeff Kirsher <jeffrey.t.kirsher@intel.com> | 2011-09-28 23:09:59 -0700 |
| commit | 9da712d2ede7e3e3a0da180351505310ee271773 (patch) | |
| tree | b1892a255c4d20c71b66d8a96c0554cc42463863 /drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h | |
| parent | ixgbe: disable LLI for FCoE (diff) | |
| download | linux-dev-9da712d2ede7e3e3a0da180351505310ee271773.tar.xz linux-dev-9da712d2ede7e3e3a0da180351505310ee271773.zip | |
ixgbe: update {P}FC thresholds to account for X540 and loopback
Revise high and low threshold marks wrt flow control to account
for the X540 devices and latency introduced by the loopback
switch.
Without this it was in theory possible to drop frames on a
supposedly lossless link with X540 or SR-IOV enabled.
Previously we used a magic number in a define to calculate the
threshold values. This made it difficult to sort out exactly
which latencies were or were not being accounted for. Here
I was overly explicit and tried to used #define names that would
be recognizable after reading the IEEE 802.1Qbb specification.
Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Tested-by: Ross Brattain <ross.b.brattain@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h')
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h index 0a68aa7f5d18..df095a9bbe2b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h @@ -36,7 +36,6 @@ #define IXGBE_MAX_PACKET_BUFFERS 8 #define MAX_USER_PRIORITY 8 -#define MAX_TRAFFIC_CLASS 8 #define MAX_BW_GROUP 8 #define BW_PERCENT 100 |