Searched full:traffic (Results 1 – 25 of 996) sorted by relevance
12345678910>>...40
| /Linux-v5.10/drivers/net/ethernet/intel/ixgbe/ |
| D | ixgbe_dcb_82598.c | 12 * @refill: refill credits index by traffic class
13 * @max: max credits index by traffic class
14 * @prio_type: priority type indexed by traffic class
16 * Configure Rx Data Arbiter and credits for each traffic class.
41 /* Configure traffic class credits and priority */ in ixgbe_dcb_config_rx_arbiter_82598()
71 * @refill: refill credits index by traffic class
72 * @max: max credits index by traffic class
73 * @bwg_id: bandwidth grouping indexed by traffic class
74 * @prio_type: priority type indexed by traffic class
76 * Configure Tx Descriptor Arbiter and credits for each traffic class.
[all …]
|
| D | ixgbe_dcb_82599.c | 12 * @refill: refill credits index by traffic class
13 * @max: max credits index by traffic class
14 * @bwg_id: bandwidth grouping indexed by traffic class
15 * @prio_type: priority type indexed by traffic class
18 * Configure Rx Packet Arbiter and credits for each traffic class.
39 /* Map all traffic classes to their UP */ in ixgbe_dcb_config_rx_arbiter_82599()
45 /* Configure traffic class credits and priority */ in ixgbe_dcb_config_rx_arbiter_82599()
72 * @refill: refill credits index by traffic class
73 * @max: max credits index by traffic class
74 * @bwg_id: bandwidth grouping indexed by traffic class
[all …]
|
| D | ixgbe_dcb.h | 28 /* Error in traffic class bandwidth allocation */
30 /* Traffic class has both link strict and group strict enabled */
32 /* Link strict traffic class has non zero bandwidth */
36 /* Traffic class has zero bandwidth */
67 * If 8 traffic classes can be configured, the value is 0x80.
73 /* Traffic class bandwidth allocation per direction */
78 u8 up_to_tc_bitmap; /* User Priority to Traffic Class mapping */
92 /* Traffic class configuration */
98 u8 tc; /* Traffic class (TC) */
|
| /Linux-v5.10/include/uapi/linux/ |
| D | dcbnl.h | 39 * @tc_tx_bw: tc tx bandwidth indexed by traffic class
40 * @tc_rx_bw: tc rx bandwidth indexed by traffic class
41 * @tc_tsa: TSA Assignment table, indexed by traffic class
42 * @prio_tc: priority assignment table mapping 8021Qp to traffic class
43 * @tc_reco_bw: recommended tc bandwidth indexed by traffic class for TLV
44 * @tc_reco_tsa: recommended tc bandwidth indexed by traffic class for TLV
45 * @reco_prio_tc: recommended tc tx bandwidth indexed by traffic class for TLV
76 * @tc_maxrate: maximal tc tx bandwidth indexed by traffic class
115 * outgoing traffic, to specifically identify outgoing
148 * @pfc_cap: Indicates the number of traffic classes on the local device
[all …]
|
| /Linux-v5.10/Documentation/networking/device_drivers/ethernet/freescale/ |
| D | dpaa.rst | 159 different traffic flows received by one interface to be processed by different
162 The driver has support for multiple prioritized Tx traffic classes. Priorities
164 strict priority levels. Each traffic class contains NR_CPU TX queues. By
165 default, only one traffic class is enabled and the lowest priority Tx queues
166 are used. Higher priority traffic classes can be enabled with the mqprio
167 qdisc. For example, all four traffic classes are enabled on an interface with
168 the following command. Furthermore, skb priority levels are mapped to traffic
171 * priorities 0 to 3 - traffic class 0 (low priority)
172 * priorities 4 to 7 - traffic class 1 (medium-low priority)
173 * priorities 8 to 11 - traffic class 2 (medium-high priority)
[all …]
|
| /Linux-v5.10/Documentation/admin-guide/cgroup-v1/ |
| D | net_prio.rst | 6 dynamically set the priority of network traffic generated by various
9 Nominally, an application would set the priority of its traffic via the
13 2) The priority of application traffic is often a site-specific administrative
17 the priority of egress traffic on a given interface. Network priority groups can
34 This file contains a map of the priorities assigned to traffic originating
42 This command would force any traffic originating from processes belonging to the
44 said traffic set to the value 5. The parent accounting group also has a
53 traffic to be steered to hardware/driver based traffic classes. These mappings
|
| /Linux-v5.10/Documentation/networking/device_drivers/ethernet/intel/ |
| D | e1000e.rst | 64 all traffic types, but lacking in small packet performance and latency.
69 it dynamically adjusts the InterruptThrottleRate value based on the traffic
70 that it receives. After determining the type of incoming traffic in the last
72 for that traffic.
74 The algorithm classifies the incoming traffic every interval into
76 adjusted to suit that traffic type the best. There are three classes defined:
77 "Bulk traffic", for large amounts of packets of normal size; "Low latency",
78 for small amounts of traffic and/or a significant percentage of small
80 minimal traffic.
84 However, this is generally not suitable for bulk throughput traffic due
[all …]
|
| D | e1000.rst | 111 all traffic types,but lacking in small packet performance and latency.
116 it dynamically adjusts the InterruptThrottleRate value based on the traffic
117 that it receives. After determining the type of incoming traffic in the last
119 for that traffic.
121 The algorithm classifies the incoming traffic every interval into
123 adjusted to suit that traffic type the best. There are three classes defined:
124 "Bulk traffic", for large amounts of packets of normal size; "Low latency",
125 for small amounts of traffic and/or a significant percentage of small
127 minimal traffic.
130 for traffic that falls in class "Bulk traffic". If traffic falls in the "Low
[all …]
|
| D | iavf.rst | 107 - 1 Traffic Class (TC), TC0
121 allow L2 tunneling and the ability to segregate traffic within a particular
139 and allow Tx traffic to be rate limited per application. Follow the steps below
155 1. Create traffic classes (TCs). Maximum of 8 TCs can be created per interface.
209 for VXLAN traffic in non-tunnel mode, PCTYPE is identified as a VXLAN
212 - If a TC filter on a PF matches traffic over a VF (on the PF), that traffic
214 the VF. Such traffic will end up getting dropped higher up in the TCP/IP
216 - If traffic matches multiple TC filters that point to different TCs, that
217 traffic will be duplicated and sent to all matching TC queues. The hardware
234 Traffic Is Not Being Passed Between VM and Client
[all …]
|
| D | ixgbe.rst | 232 the DCB features (multiple traffic classes utilizing Priority Flow Control and
235 When DCB is enabled, network traffic is transmitted and received through
236 multiple traffic classes (packet buffers in the NIC). The traffic is associated
238 in the VLAN tag. When SR-IOV is not enabled, each traffic class is associated
240 pairs for a given traffic class depends on the hardware configuration. When
243 receive/transmit descriptor queue pairs. When multiple traffic classes are
245 each traffic class. When a single traffic class is configured in the hardware,
246 the pools contain multiple queue pairs from the single traffic class.
248 The number of VFs that can be allocated depends on the number of traffic
249 classes that can be enabled. The configurable number of traffic classes for
[all …]
|
| D | i40e.rst | 103 ingress traffic, use the following command::
121 this example is that the VF will get all traffic that is tagged with VLAN 100.
139 NOTE: The Linux i40e driver allows you to filter traffic based on a
187 Sideband Perfect Filters are used to direct traffic that matches specified
199 <queue> - the queue to direct traffic towards (-1 discards matching traffic)
212 The following example matches TCP traffic sent from 192.168.0.1, port 5300,
278 To create filters that direct traffic to a specific Virtual Function, use the
285 specifies to direct traffic to Virtual Function 7 (8 minus 1) into queue 2 of
289 route traffic that otherwise would not have been sent to the specified Virtual
353 Retrieves the hash options for the specified network traffic type.
[all …]
|
| /Linux-v5.10/tools/testing/selftests/drivers/net/mlxsw/ |
| D | qos_mc_aware.sh | 5 # causes throughput of UC traffic to drop severely when a switch is under heavy
11 # Because mlxsw throttles CPU port, the traffic can't actually reach userspace
17 # So instead we send traffic with mausezahn and use RX ethtool counters at $h3.
18 # Multicast traffic is untagged, unicast traffic is tagged with PCP 1. Therefore
20 # measure the throughput. In order to avoid prioritizing unicast traffic, prio
26 # multicast traffic uses 8K frames.
31 # | multicast | | traffic | 192.0.2.129/28 |
32 # | traffic | | | e-qos-map 0:1 |
147 # room for both streams of traffic to be admitted to shared buffer.
266 check_err $(bc <<< "$deg > 25") "MC traffic degrades UC performance too much"
|
| D | sch_red_core.sh | 3 # This test sends a >1Gbps stream of traffic from H1, to the switch, which
7 # This way, $swp3 should be 100% filled with traffic without any of it spilling
9 # is what H2 is used for--it sends the extra traffic to create backlog.
19 # different configurations. Traffic is prioritized using 802.1p and relies on
126 # Some of the tests in this suite use multicast traffic. As this traffic
128 # e.g. traffic ingressing through $swp2 is flooded to $swp3 (the
130 # another stream of traffic).
353 # This sends traffic in an attempt to build a backlog of $size. Returns 0 on
415 # limit is misconfigured, we would see this traffic being ECN marked.
423 # Now push TCP, because non-TCP traffic would be early-dropped after the
[all …]
|
| D | qos_pfc.sh | 4 # This test injects a 10-MB burst of traffic with VLAN tag and 802.1p priority
11 # to a small pool ("PFC pool"). The traffic is forwarded to $swp2, which is
15 # - since $swp3 now can't send traffic, the traffic ingressing $swp1 is kept at
19 # - eventually the PFC pool gets some traffic out, headroom therefore gets some
20 # traffic to the pool, and $swp3 is unpaused again. This way the traffic is
68 # iPOOL0+ePOOL4 is a helper pool for control traffic etc.
144 # Control traffic pools. Just reduce the size. Keep them dynamic so that
|
| /Linux-v5.10/net/batman-adv/ |
| D | types.h | 769 * enum batadv_counters - indices for traffic counters
772 /** @BATADV_CNT_TX: transmitted payload traffic packet counter */
775 /** @BATADV_CNT_TX_BYTES: transmitted payload traffic bytes counter */
779 * @BATADV_CNT_TX_DROPPED: dropped transmission payload traffic packet
784 /** @BATADV_CNT_RX: received payload traffic packet counter */
787 /** @BATADV_CNT_RX_BYTES: received payload traffic bytes counter */
790 /** @BATADV_CNT_FORWARD: forwarded payload traffic packet counter */
794 * @BATADV_CNT_FORWARD_BYTES: forwarded payload traffic bytes counter
799 * @BATADV_CNT_MGMT_TX: transmitted routing protocol traffic packet
805 * @BATADV_CNT_MGMT_TX_BYTES: transmitted routing protocol traffic bytes
[all …]
|
| /Linux-v5.10/drivers/net/ethernet/mellanox/mlx4/ |
| D | fw_qos.h | 57 * mlx4_SET_PORT_PRIO2TC - This routine maps user priorities to traffic
70 * traffic classes (ETS) and configured rate limit for traffic classes.
76 * @tc_tx_bw: The percentage of the bandwidth allocated for traffic class
77 * within a TC group. The sum of the bw_percentage of all the traffic
79 * @pg: The TC group the traffic class is associated with.
80 * @ratelimit: The maximal bandwidth allowed for the use by this traffic class.
|
| /Linux-v5.10/tools/perf/pmu-events/arch/x86/knightslanding/ |
| D | uncore-memory.json | 3 "BriefDescription": "ddr bandwidth read (CPU traffic only) (MB/sec). ",
13 "BriefDescription": "ddr bandwidth write (CPU traffic only) (MB/sec). ",
23 "BriefDescription": "mcdram bandwidth read (CPU traffic only) (MB/sec). ",
33 "BriefDescription": "mcdram bandwidth write (CPU traffic only) (MB/sec). ",
|
| /Linux-v5.10/drivers/net/wireless/broadcom/brcm80211/brcmfmac/ |
| D | fwsignal.h | 13 * @BRCMF_FWS_FIFO_AC_BK: fifo for background traffic.
14 * @BRCMF_FWS_FIFO_AC_BE: fifo for best-effort traffic.
15 * @BRCMF_FWS_FIFO_AC_VI: fifo for video traffic.
16 * @BRCMF_FWS_FIFO_AC_VO: fifo for voice traffic.
|
| /Linux-v5.10/Documentation/networking/dsa/ |
| D | sja1105.rst | 66 Traffic support
72 These are used to trap BPDUs and PTP traffic to the master netdevice, and are
78 format based on VLANs), general-purpose traffic termination through the network
89 other than STP, PTP etc) traffic termination is not possible through the
100 To summarize, in each mode, the following types of traffic are supported over
107 | traffic | | (use master) | |
110 | traffic | | | |
269 The hardware tags all traffic internally with a port-based VLAN (pvid), or it
278 bridge with ``vlan_filtering 0`` can be kept (accept all traffic, tagged or
286 ports are no longer available for standalone traffic termination.
[all …]
|
| D | configuration.rst | 55 A slave interface dedicated for upstream traffic
78 DSA switches. These switches are capable to tag incoming and outgoing traffic
170 # tag traffic on CPU port
197 # tag traffic on ports
216 # tag traffic on CPU port
240 # tag traffic on ports
256 # tag traffic on CPU port
282 # tag traffic on ports
|
| /Linux-v5.10/Documentation/networking/ |
| D | bonding.rst | 286 traffic recently (the precise criteria depends upon the
287 bonding mode, and the state of the slave). Regular traffic is
319 non-ARP traffic should be filtered (disregarded) for link
359 is receiving the appropriate ARP traffic.
378 target fail (but not the switch itself), the probe traffic
394 determining if a slave has received traffic for link availability
398 levels of third party broadcast traffic would fool the standard
400 filtering can resolve this, as only ARP traffic is considered for
465 often takes place for any traffic, not just ARP
466 traffic, if the switch snoops incoming traffic to
[all …]
|
| D | af_xdp.rst | 55 completed that traffic starts to flow.
79 traffic to user space through the XSK.
318 built in one in libbpf that will route the traffic for you.
398 both, you will be able to both receive and send traffic from your
540 you would like your UDP traffic from port 4242 to end up in queue 16,
563 Q: I am not seeing any traffic on the socket. What am I doing wrong?
569 specify a specific queue id to bind to and it is only the traffic
572 traffic that is distributed to queues 1 through 7. If you are
573 lucky, you will see the traffic, but usually it will end up on one
577 traffic you want to the queue id you bound to. If you want to see
[all …]
|
| /Linux-v5.10/net/bridge/ |
| D | Kconfig | 30 bridged ARP traffic in the arptables FORWARD chain.
44 forward multicast traffic based on IGMP/MLD traffic received from
58 receive and forward traffic based on VLAN information in the packet
|
| /Linux-v5.10/drivers/net/ethernet/freescale/dpaa2/ |
| D | dpni.h | 21 * Maximum number of traffic classes
30 * All traffic classes considered; see dpni_set_queue()
34 * All flows within traffic class considered; see dpni_set_queue()
43 * Tx traffic is always released to a buffer pool on transmit, there are no
52 * is disabled, only traffic matching the primary MAC address will be accepted.
56 * Allocate policers for this DPNI. They can be used to rate-limit traffic per
57 * traffic class (TC) basis.
65 * DPNI has multiple traffic classes.
79 * Flow steering table is shared between all traffic classes
193 * @num_queues: Number of Tx and Rx queues used for traffic distribution.
[all …]
|
| /Linux-v5.10/drivers/gpu/drm/msm/disp/dpu1/ |
| D | dpu_hw_top.h | 16 * struct traffic_shaper_cfg: traffic shaper configuration
17 * @en : enable/disable traffic shaper
76 * @setup_traffic_shaper : programs traffic shaper control
88 * setup_traffic_shaper() : Setup traffic shaper control
90 * @cfg : traffic shaper configuration
|
12345678910>>...40
