Linux Driver Software: Broadcom NetXtreme II Network Adapter User Guide
file:///T|/htdocs/NETWORK/BroadCom/71921/NetXtremeII/en/linux.htm[9/26/2012 3:28:46 PM]
modprobe bnx2x int_mode=2
Set the
int_mode
parameter to 3 to force using MSI-X mode on all NetXtreme II adapters in the system.
dropless_fc
The
dropless_fc
parameter can be used to enable a complementary flow control mechanism on BCM57711/BCM57712
adapters. The default flow control mechanism is to send pause frames when the on-chip buffer (BRB) is reaching a certain
level of occupancy. This is a performance targeted flow control mechanism. On BCM57711/BCM57712 adapters, one can
enable another flow control mechanism to send pause frames, where one of the host buffers (when in RSS mode) are
exhausted.
This is a "zero packet drop" targeted flow control mechanism.
Set the
dropless_fc
parameter to 1 to enable the dropless flow control mechanism feature on all BCM57711/BCM57712
NetXtreme II adapters in the system.
insmod bnx2x.ko dropless_fc=1
or
modprobe bnx2x dropless_fc=1
disable_iscsi_ooo
The
disable_iscsi_ooo
parameter
is to disable the allocation of the iSCSI TCP Out-of-Order (OOO) reception resources,
specifically for VMware for low-memory systems.
multi_mode
The optional parameter
multi_mode
is for use on systems that support multi-queue networking. Multi-queue networking on
the receive side depends only on MSI-X cability of the system, multi-queue networking on the transmit side is supported only
on kernels starting from 2.6.27. By default,
multi_mode
parameter is set to 1. Thus, on kernels up to 2.6.26, the driver will
allocate on the receive side one queue per-CPU and on the transmit side only one queue. On kernels starting from 2.6.27, the
driver will allocate on both receive and transmit sides, one queue per-CPU. In any case, the number of allocated queues will
be limited by number of queues supported by hardware.
The
multi_mode
optional parameter can also be used to enable SAFC (Service Aware Flow Control) by differentiating the
traffic to up to 3 CoS (Class of Service) in the hardware according to the VLAN PRI value or according to the IP DSCP value
(least 3 bits).
num_queues
The optional parameter
num_queues
may be used to set the number of queues when
multi_mode
is set to 1 and interrupt
mode is MSI-X. If interrupt mode is different than MSI-X (see
int_mode
), the number of queues will be set to 1, discarding
the value of this parameter.
pri_map
The optional parameter
pri_map
is used to map the VLAN PRI value or the IP DSCP value to a different or same CoS in the
hardware. This 32-bit parameter is evaluated by the driver as an 8 value of 4 bits each. Each nibble sets the desired hardware
queue number for that priority. For example, set
pri_map
to 0x11110000 to map priority 0 to 3 to CoS 0 and map priority 4
to 7 to CoS 1.
qs_per_cos
The optional parameter
qs_per_cos
is used to specify how many queues will share the same CoS. This parameter is
evaluated by the driver up to 3 values of 8 bits each. Each byte sets the desired number of queues for that CoS. The total
number of queues is limited by the hardware limit. For example, set
qs_per_cos
to 0x10101 to create a total of three
queues, one per CoS. In another example, set
qs_per_cos
to 0x404 to create a total of 8 queues, divided into 2 CoS, 4
queues in each CoS.
cos_min_rate
The optional parameter
cos_min_rate
is used to determine the weight of each CoS for round-robin scheduling in
transmission. This parameter is evaluated by the driver as up to 3 values of 8 bits each. Each byte sets the desired weight for
that CoS. The weight ranges from 0 to 100. For example, set
cos_min_rate
to 0x101 for fair transmission rate between 2
CoS. In another example, set the
cos_min_rate
to 0x30201 to give CoS the higher rate of transmission. To avoid using the
fairness algorithm, omit setting
cos_min_rate
or set it to 0.