1ETHTOOL(8) System Manager's Manual ETHTOOL(8)
2
3
4
6 ethtool - query or control network driver and hardware settings
7
9 ethtool devname
10
11 ethtool -h|--help
12
13 ethtool --version
14
15 ethtool [--debug N] args
16
17 ethtool [--json] args
18
19 ethtool [-I | --include-statistics] args
20
21 ethtool --monitor [ command ] [ devname ]
22
23 ethtool -a|--show-pause devname
24
25 ethtool -A|--pause devname [autoneg on|off] [rx on|off] [tx on|off]
26
27 ethtool -c|--show-coalesce devname
28
29 ethtool -C|--coalesce devname [adaptive-rx on|off] [adaptive-tx on|off]
30 [rx-usecs N] [rx-frames N] [rx-usecs-irq N] [rx-frames-irq N]
31 [tx-usecs N] [tx-frames N] [tx-usecs-irq N] [tx-frames-irq N]
32 [stats-block-usecs N] [pkt-rate-low N] [rx-usecs-low N]
33 [rx-frames-low N] [tx-usecs-low N] [tx-frames-low N]
34 [pkt-rate-high N] [rx-usecs-high N] [rx-frames-high N]
35 [tx-usecs-high N] [tx-frames-high N] [sample-interval N]
36 [cqe-mode-rx on|off] [cqe-mode-tx on|off] [tx-aggr-max-bytes N]
37 [tx-aggr-max-frames N] [tx-aggr-time-usecs N]
38
39 ethtool -g|--show-ring devname
40
41 ethtool -G|--set-ring devname [rx N] [rx-mini N] [rx-jumbo N] [tx N]
42 [rx-buf-len N] [cqe-size N] [tx-push N] [rx-push N]
43 [tx-push-buf-len N]
44
45 ethtool -i|--driver devname
46
47 ethtool -d|--register-dump devname [raw on|off] [hex on|off] [file
48 name]
49
50 ethtool -e|--eeprom-dump devname [raw on|off] [offset N] [length N]
51
52 ethtool -E|--change-eeprom devname [magic N] [offset N] [length N]
53 [value N]
54
55 ethtool -k|--show-features|--show-offload devname
56
57 ethtool -K|--features|--offload devname feature on|off ...
58
59 ethtool -p|--identify devname [N]
60
61 ethtool -P|--show-permaddr devname
62
63 ethtool -r|--negotiate devname
64
65 ethtool -S|--statistics devname [--all-groups|--groups [eth-phy]
66 [eth-mac] [eth-ctrl] [rmon] ]
67
68 ethtool --phy-statistics devname
69
70 ethtool -t|--test devname [offline|online|external_lb]
71
72 ethtool -s devname [speed N] [lanes N] [duplex half|full]
73 [port tp|aui|bnc|mii] [mdix auto|on|off] [autoneg on|off]
74 [advertise N[/M] | advertise mode on|off ...] [phyad N]
75 [xcvr internal|external] [wol N[/M] | wol p|u|m|b|a|g|s|f|d...]
76 [sopass xx:yy:zz:aa:bb:cc] [master-slave preferred-
77 master|preferred-slave|forced-master|forced-slave] [msglvl
78 N[/M] | msglvl type on|off ...]
79
80 ethtool -n|-u|--show-nfc|--show-ntuple devname
81 [ rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6 |
82 rule N ]
83
84 ethtool -N|-U|--config-nfc|--config-ntuple devname
85 rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6
86 m|v|t|s|d|f|n|r... |
87 flow-type
88 ether|ip4|tcp4|udp4|sctp4|ah4|esp4|ip6|tcp6|udp6|ah6|esp6|sctp6
89 [src xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]]
90 [dst xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]] [proto N [m N]]
91 [src-ip ip-address [m ip-address]] [dst-ip ip-address [m ip-
92 address]] [tos N [m N]] [tclass N [m N]] [l4proto N [m N]]
93 [src-port N [m N]] [dst-port N [m N]] [spi N [m N]]
94 [l4data N [m N]] [vlan-etype N [m N]] [vlan N [m N]]
95 [user-def N [m N]] [dst-
96 mac xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]] [action N]
97 [context N] [loc N] |
98 delete N
99
100 ethtool -w|--get-dump devname [data filename]
101
102 ethtool -W|--set-dump devname N
103
104 ethtool -T|--show-time-stamping devname
105
106 ethtool -x|--show-rxfh-indir|--show-rxfh devname
107
108 ethtool -X|--set-rxfh-indir|--rxfh devname [hkey xx:yy:zz:aa:bb:cc:...]
109 [start N] [ equal N | weight W0 W1 ... | default ] [hfunc FUNC]
110 [context CTX | new] [delete]
111
112 ethtool -f|--flash devname file [N]
113
114 ethtool -l|--show-channels devname
115
116 ethtool -L|--set-channels devname [rx N] [tx N] [other N] [combined N]
117
118 ethtool -m|--dump-module-eeprom|--module-info devname [raw on|off]
119 [hex on|off] [offset N] [length N] [page N] [bank N] [i2c N]
120
121 ethtool --show-priv-flags devname
122
123 ethtool --set-priv-flags devname flag on|off ...
124
125 ethtool --show-eee devname
126
127 ethtool --set-eee devname [eee on|off] [tx-lpi on|off] [tx-timer N]
128 [advertise N]
129
130 ethtool --set-phy-tunable devname [ downshift on|off [count N] ] [
131 fast-link-down on|off [msecs N] ] [ energy-detect-power-down
132 on|off [msecs N] ]
133
134 ethtool --get-phy-tunable devname [downshift] [fast-link-down] [energy-
135 detect-power-down]
136
137 ethtool --get-tunable devname [rx-copybreak] [tx-copybreak] [tx-buf-
138 size] [pfc-prevention-tout]
139
140 ethtool --set-tunable devname [rx-copybreak N] [tx-copybreak N]
141 [tx-buf-size N] [pfc-prevention-tout N]
142
143 ethtool --reset devname [flags N] [mgmt] [mgmt-shared] [irq] [irq-
144 shared] [dma] [dma-shared] [filter] [filter-shared] [offload]
145 [offload-shared] [mac] [mac-shared] [phy] [phy-shared] [ram]
146 [ram-shared] [ap] [ap-shared] [dedicated] [all]
147
148 ethtool --show-fec devname
149
150 ethtool --set-fec devname encoding auto|off|rs|baser|llrs [...]
151
152 ethtool -Q|--per-queue devname [queue_mask %x] sub_command ...
153
154 ethtool --cable-test devname
155
156 ethtool --cable-test-tdr devname [first N] [last N] [step N] [pair N]
157
158 ethtool --show-tunnels devname
159
160 ethtool --show-module devname
161
162 ethtool --set-module devname [power-mode-policy high|auto]
163
164 ethtool --get-plca-cfg devname
165
166 ethtool --set-plca-cfg devname [enable on|off] [node-id N] [node-cnt N]
167 [to-tmr N] [burst-cnt N] [burst-tmr N]
168
169 ethtool --get-plca-status devname
170
171 ethtool --show-mm devname
172
173 ethtool --set-mm devname [verify-enabled on|off] [verify-time N]
174 [tx-enabled on|off] [pmac-enabled on|off] [tx-min-frag-size N]
175
176 ethtool --show-pse devname
177
178 ethtool --set-pse devname [podl-pse-admin-control enable|disable]
179
180
182 ethtool is used to query and control network device driver and hardware
183 settings, particularly for wired Ethernet devices.
184
185 devname is the name of the network device on which ethtool should oper‐
186 ate.
187
188
190 ethtool with a single argument specifying the device name prints cur‐
191 rent settings of the specified device.
192
193 -h --help
194 Shows a short help message.
195
196 --version
197 Shows the ethtool version number.
198
199 --debug N
200 Turns on debugging messages. Argument is interpreted as a mask:
201
202 0x01 Parser information
203
204 --json Output results in JavaScript Object Notation (JSON). Only a sub‐
205 set of options support this. Those which do not will continue to
206 output plain text in the presence of this option.
207
208 -I --include-statistics
209 Include command-related statistics in the output. This option
210 allows displaying relevant device statistics for selected get
211 commands.
212
213 -a --show-pause
214 Queries the specified Ethernet device for pause parameter infor‐
215 mation.
216
217 --src aggregate|emac|pmac
218 If the MAC Merge layer is supported, request a particular
219 source of device statistics (eMAC or pMAC, or their aggre‐
220 gate). Only valid if ethtool was invoked with the -I --in‐
221 clude-statistics argument.
222
223 -A --pause
224 Changes the pause parameters of the specified Ethernet device.
225
226 autoneg on|off
227 Specifies whether pause autonegotiation should be enabled.
228
229 rx on|off
230 Specifies whether RX pause should be enabled.
231
232 tx on|off
233 Specifies whether TX pause should be enabled.
234
235 -c --show-coalesce
236 Queries the specified network device for coalescing information.
237
238 -C --coalesce
239 Changes the coalescing settings of the specified network device.
240
241 -g --show-ring
242 Queries the specified network device for rx/tx ring parameter
243 information.
244
245 -G --set-ring
246 Changes the rx/tx ring parameters of the specified network de‐
247 vice.
248
249 rx N Changes the number of ring entries for the Rx ring.
250
251 rx-mini N
252 Changes the number of ring entries for the Rx Mini ring.
253
254 rx-jumbo N
255 Changes the number of ring entries for the Rx Jumbo ring.
256
257 tx N Changes the number of ring entries for the Tx ring.
258
259 rx-buf-len N
260 Changes the size of a buffer in the Rx ring.
261
262 cqe-size N
263 Changes the size of completion queue event.
264
265 tx-push on|off
266 Specifies whether TX push should be enabled.
267
268 rx-push on|off
269 Specifies whether RX push should be enabled.
270
271 tx-push-buf-len N
272 Specifies the maximum number of bytes of a transmitted pack‐
273 et a driver can push directly to the underlying device
274
275 -i --driver
276 Queries the specified network device for associated driver in‐
277 formation.
278
279 -d --register-dump
280 Retrieves and prints a register dump for the specified network
281 device. The register format for some devices is known and de‐
282 coded others are printed in hex. When raw is enabled, then eth‐
283 tool dumps the raw register data to stdout. If file is speci‐
284 fied, then use contents of previous raw register dump, rather
285 than reading from the device.
286
287 -e --eeprom-dump
288 Retrieves and prints an EEPROM dump for the specified network
289 device. When raw is enabled, then it dumps the raw EEPROM data
290 to stdout. The length and offset parameters allow dumping cer‐
291 tain portions of the EEPROM. Default is to dump the entire EEP‐
292 ROM.
293
294 raw on|off
295
296 offset N
297
298 length N
299
300 -E --change-eeprom
301 If value is specified, changes EEPROM byte for the specified
302 network device. offset and value specify which byte and it's
303 new value. If value is not specified, stdin is read and written
304 to the EEPROM. The length and offset parameters allow writing to
305 certain portions of the EEPROM. Because of the persistent na‐
306 ture of writing to the EEPROM, a device-specific magic key must
307 be specified to prevent the accidental writing to the EEPROM.
308
309 -k --show-features --show-offload
310 Queries the specified network device for the state of protocol
311 offload and other features.
312
313 -K --features --offload
314 Changes the offload parameters and other features of the speci‐
315 fied network device. The following feature names are built-in
316 and others may be defined by the kernel.
317
318 rx on|off
319 Specifies whether RX checksumming should be enabled.
320
321 tx on|off
322 Specifies whether TX checksumming should be enabled.
323
324 sg on|off
325 Specifies whether scatter-gather should be enabled.
326
327 tso on|off
328 Specifies whether TCP segmentation offload should be en‐
329 abled.
330
331 ufo on|off
332 Specifies whether UDP fragmentation offload should be en‐
333 abled
334
335 gso on|off
336 Specifies whether generic segmentation offload should be en‐
337 abled
338
339 gro on|off
340 Specifies whether generic receive offload should be enabled
341
342 lro on|off
343 Specifies whether large receive offload should be enabled
344
345 rxvlan on|off
346 Specifies whether RX VLAN acceleration should be enabled
347
348 txvlan on|off
349 Specifies whether TX VLAN acceleration should be enabled
350
351 ntuple on|off
352 Specifies whether Rx ntuple filters and actions should be
353 enabled
354
355 rxhash on|off
356 Specifies whether receive hashing offload should be enabled
357
358 -p --identify
359 Initiates adapter-specific action intended to enable an operator
360 to easily identify the adapter by sight. Typically this in‐
361 volves blinking one or more LEDs on the specific network port.
362
363 [ N] Length of time to perform phys-id, in seconds.
364
365 -P --show-permaddr
366 Queries the specified network device for permanent hardware ad‐
367 dress.
368
369 -r --negotiate
370 Restarts auto-negotiation on the specified Ethernet device, if
371 auto-negotiation is enabled.
372
373 -S --statistics
374 Queries the specified network device for standard (IEEE, IETF,
375 etc.), or NIC- and driver-specific statistics. NIC- and driver-
376 specific statistics are requested when no group of statistics is
377 specified.
378
379 NIC- and driver-specific statistics and standard statistics are
380 independent, devices may implement either, both or none. There
381 is little commonality between naming of NIC- and driver-specific
382 statistics across vendors.
383
384 --all-groups
385
386 --groups [eth-phy] [eth-mac] [eth-ctrl] [rmon]
387 Request groups of standard device statistics.
388
389 --src aggregate|emac|pmac
390 If the MAC Merge layer is supported, request a particular
391 source of device statistics (eMAC or pMAC, or their aggre‐
392 gate).
393
394 --phy-statistics
395 Queries the specified network device for PHY specific statis‐
396 tics.
397
398 -t --test
399 Executes adapter selftest on the specified network device. Pos‐
400 sible test modes are:
401
402 offline
403 Perform full set of tests, possibly interrupting normal op‐
404 eration during the tests,
405
406 online Perform limited set of tests, not interrupting normal opera‐
407 tion,
408
409 external_lb
410 Perform full set of tests, as for offline, and additionally
411 an external-loopback test.
412
413 -s --change
414 Allows changing some or all settings of the specified network
415 device. All following options only apply if -s was specified.
416
417 speed N
418 Set speed in Mb/s. ethtool with just the device name as an
419 argument will show you the supported device speeds.
420
421 lanes N
422 Set number of lanes.
423
424 duplex half|full
425 Sets full or half duplex mode.
426
427 port tp|aui|bnc|mii
428 Selects device port.
429
430 master-slave preferred-master|preferred-slave|forced-master|forced-
431 slave
432 Configure MASTER/SLAVE role of the PHY. When the PHY is con‐
433 figured as MASTER, the PMA Transmit function shall source
434 TX_TCLK from a local clock source. When configured as SLAVE,
435 the PMA Transmit function shall source TX_TCLK from the
436 clock recovered from data stream provided by MASTER. Not all
437 devices support this.
438
439 preferred-master Prefer MASTER role on autonegotiation
440 preferred-slave Prefer SLAVE role on autonegotiation
441 forced-master Force the PHY in MASTER role. Can be used without autonegotiation
442 forced-slave Force the PHY in SLAVE role. Can be used without autonegotiation
443
444 mdix auto|on|off
445 Selects MDI-X mode for port. May be used to override the au‐
446 tomatic detection feature of most adapters. An argument of
447 auto means automatic detection of MDI status, on forces MDI-
448 X (crossover) mode, while off means MDI (straight through)
449 mode. The driver should guarantee that this command takes
450 effect immediately, and if necessary may reset the link to
451 cause the change to take effect.
452
453 autoneg on|off
454 Specifies whether autonegotiation should be enabled. Autone‐
455 gotiation is enabled by default, but in some network devices
456 may have trouble with it, so you can disable it if really
457 necessary.
458
459 advertise N
460 Sets the speed and duplex advertised by autonegotiation.
461 The argument is a hexadecimal value using one or a combina‐
462 tion of the following values:
463
464 0x001 10baseT Half
465 0x002 10baseT Full
466 0x100000000000000000000000 10baseT1L Full
467 0x8000000000000000000000000 10baseT1S Full
468 0x10000000000000000000000000 10baseT1S Half
469 0x20000000000000000000000000 10baseT1S_P2MP Half
470 0x004 100baseT Half
471 0x008 100baseT Full
472 0x80000000000000000 100baseT1 Full
473 0x40000000000000000000000 100baseFX Half
474 0x80000000000000000000000 100baseFX Full
475 0x010 1000baseT Half (not supported by IEEE standards)
476 0x020 1000baseT Full
477 0x20000 1000baseKX Full
478 0x20000000000 1000baseX Full
479 0x100000000000000000 1000baseT1 Full
480 0x8000 2500baseX Full (not supported by IEEE standards)
481 0x800000000000 2500baseT Full
482 0x1000000000000 5000baseT Full
483 0x1000 10000baseT Full
484 0x40000 10000baseKX4 Full
485 0x80000 10000baseKR Full
486 0x100000 10000baseR_FEC
487 0x40000000000 10000baseCR Full
488 0x80000000000 10000baseSR Full
489 0x100000000000 10000baseLR Full
490 0x200000000000 10000baseLRM Full
491 0x400000000000 10000baseER Full
492 0x200000 20000baseMLD2 Full (not supported by IEEE standards)
493 0x400000 20000baseKR2 Full (not supported by IEEE standards)
494 0x80000000 25000baseCR Full
495 0x100000000 25000baseKR Full
496 0x200000000 25000baseSR Full
497 0x800000 40000baseKR4 Full
498 0x1000000 40000baseCR4 Full
499 0x2000000 40000baseSR4 Full
500 0x4000000 40000baseLR4 Full
501 0x400000000 50000baseCR2 Full
502 0x800000000 50000baseKR2 Full
503 0x10000000000 50000baseSR2 Full
504 0x10000000000000 50000baseKR Full
505 0x20000000000000 50000baseSR Full
506 0x40000000000000 50000baseCR Full
507 0x80000000000000 50000baseLR_ER_FR Full
508 0x100000000000000 50000baseDR Full
509 0x8000000 56000baseKR4 Full
510 0x10000000 56000baseCR4 Full
511 0x20000000 56000baseSR4 Full
512 0x40000000 56000baseLR4 Full
513 0x1000000000 100000baseKR4 Full
514 0x2000000000 100000baseSR4 Full
515 0x4000000000 100000baseCR4 Full
516 0x8000000000 100000baseLR4_ER4 Full
517 0x200000000000000 100000baseKR2 Full
518 0x400000000000000 100000baseSR2 Full
519 0x800000000000000 100000baseCR2 Full
520 0x1000000000000000 100000baseLR2_ER2_FR2 Full
521 0x2000000000000000 100000baseDR2 Full
522 0x8000000000000000000 100000baseKR Full
523 0x10000000000000000000 100000baseSR Full
524 0x20000000000000000000 100000baseLR_ER_FR Full
525 0x40000000000000000000 100000baseCR Full
526 0x80000000000000000000 100000baseDR Full
527 0x4000000000000000 200000baseKR4 Full
528 0x8000000000000000 200000baseSR4 Full
529 0x10000000000000000 200000baseLR4_ER4_FR4 Full
530 0x20000000000000000 200000baseDR4 Full
531 0x40000000000000000 200000baseCR4 Full
532 0x100000000000000000000 200000baseKR2 Full
533 0x200000000000000000000 200000baseSR2 Full
534 0x400000000000000000000 200000baseLR2_ER2_FR2 Full
535 0x800000000000000000000 200000baseDR2 Full
536 0x1000000000000000000000 200000baseCR2 Full
537 0x200000000000000000 400000baseKR8 Full
538 0x400000000000000000 400000baseSR8 Full
539 0x800000000000000000 400000baseLR8_ER8_FR8 Full
540 0x1000000000000000000 400000baseDR8 Full
541 0x2000000000000000000 400000baseCR8 Full
542 0x2000000000000000000000 400000baseKR4 Full
543 0x4000000000000000000000 400000baseSR4 Full
544 0x8000000000000000000000 400000baseLR4_ER4_FR4 Full
545 0x10000000000000000000000 400000baseDR4 Full
546 0x20000000000000000000000 400000baseCR4 Full
547 0x200000000000000000000000 800000baseCR8 Full
548 0x400000000000000000000000 800000baseKR8 Full
549 0x800000000000000000000000 800000baseDR8 Full
550 0x1000000000000000000000000 800000baseDR8_2 Full
551 0x2000000000000000000000000 800000baseSR8 Full
552 0x4000000000000000000000000 800000baseVR8 Full
553
554 phyad N
555 PHY address.
556
557 xcvr internal|external
558 Selects transceiver type. Currently only internal and exter‐
559 nal can be specified, in the future further types might be
560 added.
561
562 wol p|u|m|b|a|g|s|f|d...
563 Sets Wake-on-LAN options. Not all devices support this.
564 The argument to this option is a string of characters speci‐
565 fying which options to enable.
566
567 p Wake on PHY activity
568 u Wake on unicast messages
569 m Wake on multicast messages
570 b Wake on broadcast messages
571 a Wake on ARP
572 g Wake on MagicPacket™
573 s Enable SecureOn™ password for MagicPacket™
574 f Wake on filter(s)
575 d Disable (wake on nothing). This option
576 clears all previous options.
577
578 sopass xx:yy:zz:aa:bb:cc
579 Sets the SecureOn™ password. The argument to this option
580 must be 6 bytes in Ethernet MAC hex format
581 (xx:yy:zz:aa:bb:cc).
582
583 msglvl N
584 msglvl type on|off ...
585 Sets the driver message type flags by name or number. type
586 names the type of message to enable or disable; N specifies
587 the new flags numerically. The defined type names and num‐
588 bers are:
589
590 drv 0x0001 General driver status
591 probe 0x0002 Hardware probing
592 link 0x0004 Link state
593 timer 0x0008 Periodic status check
594 ifdown 0x0010 Interface being brought down
595 ifup 0x0020 Interface being brought up
596 rx_err 0x0040 Receive error
597 tx_err 0x0080 Transmit error
598 tx_queued 0x0100 Transmit queueing
599 intr 0x0200 Interrupt handling
600 tx_done 0x0400 Transmit completion
601 rx_status 0x0800 Receive completion
602 pktdata 0x1000 Packet contents
603 hw 0x2000 Hardware status
604 wol 0x4000 Wake-on-LAN status
605
606 The precise meanings of these type flags differ between
607 drivers.
608
609 -n -u --show-nfc --show-ntuple
610 Retrieves receive network flow classification options or rules.
611
612 rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6
613 Retrieves the hash options for the specified flow type.
614
615 tcp4 TCP over IPv4
616 udp4 UDP over IPv4
617 ah4 IPSEC AH over IPv4
618 esp4 IPSEC ESP over IPv4
619 sctp4 SCTP over IPv4
620 tcp6 TCP over IPv6
621 udp6 UDP over IPv6
622 ah6 IPSEC AH over IPv6
623 esp6 IPSEC ESP over IPv6
624 sctp6 SCTP over IPv6
625
626 rule N Retrieves the RX classification rule with the given ID.
627
628 -N -U --config-nfc --config-ntuple
629 Configures receive network flow classification options or rules.
630
631 rx-flow-hash tcp4|udp4|ah4|esp4|sctp4|tcp6|udp6|ah6|esp6|sctp6
632 m|v|t|s|d|f|n|r...
633 Configures the hash options for the specified flow type.
634
635 m Hash on the Layer 2 destination address of the rx packet.
636 v Hash on the VLAN tag of the rx packet.
637 t Hash on the Layer 3 protocol field of the rx packet.
638 s Hash on the IP source address of the rx packet.
639 d Hash on the IP destination address of the rx packet.
640 f Hash on bytes 0 and 1 of the Layer 4 header of the rx packet.
641 n Hash on bytes 2 and 3 of the Layer 4 header of the rx packet.
642 r Discard all packets of this flow type. When this option is
643 set, all other options are ignored.
644
645 flow-type
646 ether|ip4|tcp4|udp4|sctp4|ah4|esp4|ip6|tcp6|udp6|ah6|esp6|sctp6
647 Inserts or updates a classification rule for the specified
648 flow type.
649
650 ether Ethernet
651 ip4 Raw IPv4
652 tcp4 TCP over IPv4
653 udp4 UDP over IPv4
654 sctp4 SCTP over IPv4
655 ah4 IPSEC AH over IPv4
656 esp4 IPSEC ESP over IPv4
657 ip6 Raw IPv6
658 tcp6 TCP over IPv6
659 udp6 UDP over IPv6
660 sctp6 SCTP over IPv6
661 ah6 IPSEC AH over IPv6
662 esp6 IPSEC ESP over IPv6
663
664 For all fields that allow both a value and a mask to be specified,
665 the mask may be specified immediately after the value using the m
666 keyword, or separately using the field name keyword with -mask ap‐
667 pended, e.g. src-mask.
668
669 src xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]
670 Includes the source MAC address, specified as 6 bytes in
671 hexadecimal separated by colons, along with an optional
672 mask. Valid only for flow-type ether.
673
674 dst xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]
675 Includes the destination MAC address, specified as 6 bytes
676 in hexadecimal separated by colons, along with an optional
677 mask. Valid only for flow-type ether.
678
679 proto N [m N]
680 Includes the Ethernet protocol number (ethertype) and an op‐
681 tional mask. Valid only for flow-type ether.
682
683 src-ip ip-address [m ip-address]
684 Specify the source IP address of the incoming packet to
685 match along with an optional mask. Valid for all IP based
686 flow-types.
687
688 dst-ip ip-address [m ip-address]
689 Specify the destination IP address of the incoming packet to
690 match along with an optional mask. Valid for all IP based
691 flow-types.
692
693 tos N [m N]
694 Specify the value of the Type of Service field in the incom‐
695 ing packet to match along with an optional mask. Applies to
696 all IPv4 based flow-types.
697
698 tclass N [m N]
699 Specify the value of the Traffic Class field in the incoming
700 packet to match along with an optional mask. Applies to all
701 IPv6 based flow-types.
702
703 l4proto N [m N]
704 Includes the layer 4 protocol number and optional mask.
705 Valid only for flow-types ip4 and ip6.
706
707 src-port N [m N]
708 Specify the value of the source port field (applicable to
709 TCP/UDP packets) in the incoming packet to match along with
710 an optional mask. Valid for flow-types ip4, tcp4, udp4, and
711 sctp4 and their IPv6 equivalents.
712
713 dst-port N [m N]
714 Specify the value of the destination port field (applicable
715 to TCP/UDP packets)in the incoming packet to match along
716 with an optional mask. Valid for flow-types ip4, tcp4,
717 udp4, and sctp4 and their IPv6 equivalents.
718
719 spi N [m N]
720 Specify the value of the security parameter index field (ap‐
721 plicable to AH/ESP packets)in the incoming packet to match
722 along with an optional mask. Valid for flow-types ip4, ah4,
723 and esp4 and their IPv6 equivalents.
724
725 l4data N [m N]
726 Specify the value of the first 4 Bytes of Layer 4 in the in‐
727 coming packet to match along with an optional mask. Valid
728 for ip4 and ip6 flow-types.
729
730 vlan-etype N [m N]
731 Includes the VLAN tag Ethertype and an optional mask.
732
733 vlan N [m N]
734 Includes the VLAN tag and an optional mask.
735
736 user-def N [m N]
737 Includes 64-bits of user-specific data and an optional mask.
738
739 dst-mac xx:yy:zz:aa:bb:cc [m xx:yy:zz:aa:bb:cc]
740 Includes the destination MAC address, specified as 6 bytes
741 in hexadecimal separated by colons, along with an optional
742 mask. Valid for all IP based flow-types.
743
744 action N
745 Specifies the Rx queue to send packets to, or some other ac‐
746 tion.
747
748 -1 Drop the matched flow
749 -2 Use the matched flow as a Wake-on-LAN filter
750 0 or higher Rx queue to route the flow
751
752 context N
753 Specifies the RSS context to spread packets over multiple
754 queues; either 0 for the default RSS context, or a value re‐
755 turned by ethtool -X ... context new.
756
757 vf N Specifies the Virtual Function the filter applies to. Not
758 compatible with action.
759
760 queue N
761 Specifies the Rx queue to send packets to. Not compatible
762 with action.
763
764 loc N Specify the location/ID to insert the rule. This will over‐
765 write any rule present in that location and will not go
766 through any of the rule ordering process.
767
768 delete N
769 Deletes the RX classification rule with the given ID.
770
771 -w --get-dump
772 Retrieves and prints firmware dump for the specified network de‐
773 vice. By default, it prints out the dump flag, version and
774 length of the dump data. When data is indicated, then ethtool
775 fetches the dump data and directs it to a file.
776
777 -W --set-dump
778 Sets the dump flag for the device.
779
780 -T --show-time-stamping
781 Show the device's time stamping capabilities and associated PTP
782 hardware clock.
783
784 -x --show-rxfh-indir --show-rxfh
785 Retrieves the receive flow hash indirection table and/or RSS
786 hash key.
787
788 -X --set-rxfh-indir --rxfh
789 Configures the receive flow hash indirection table and/or RSS
790 hash key.
791
792 hkey Sets RSS hash key of the specified network device. RSS hash
793 key should be of device supported length. Hash key format
794 must be in xx:yy:zz:aa:bb:cc format meaning both the nibbles
795 of a byte should be mentioned even if a nibble is zero.
796
797 hfunc Sets RSS hash function of the specified network device.
798 List of RSS hash functions which kernel supports is shown as
799 a part of the --show-rxfh command output.
800
801 start N
802 For the equal and weight options, sets the starting receive
803 queue for spreading flows to N.
804
805 equal N
806 Sets the receive flow hash indirection table to spread flows
807 evenly between the first N receive queues.
808
809 weight W0 W1 ...
810 Sets the receive flow hash indirection table to spread flows
811 between receive queues according to the given weights. The
812 sum of the weights must be non-zero and must not exceed the
813 size of the indirection table.
814
815 default
816 Sets the receive flow hash indirection table to its default
817 value.
818
819 context CTX | new
820 Specifies an RSS context to act on; either new to allocate a
821 new RSS context, or CTX, a value returned by a previous
822 ... context new.
823
824 delete Delete the specified RSS context. May only be used in con‐
825 junction with context and a non-zero CTX value.
826
827 -f --flash
828 Write a firmware image to flash or other non-volatile memory on
829 the device.
830
831 file Specifies the filename of the firmware image. The firmware
832 must first be installed in one of the directories where the
833 kernel firmware loader or firmware agent will look, such as
834 /lib/firmware.
835
836 N If the device stores multiple firmware images in separate
837 regions of non-volatile memory, this parameter may be used
838 to specify which region is to be written. The default is 0,
839 requesting that all regions are written. All other values
840 are driver-dependent.
841
842 -l --show-channels
843 Queries the specified network device for the numbers of channels
844 it has. A channel is an IRQ and the set of queues that can
845 trigger that IRQ.
846
847 -L --set-channels
848 Changes the numbers of channels of the specified network device.
849
850 rx N Changes the number of channels with only receive queues.
851
852 tx N Changes the number of channels with only transmit queues.
853
854 other N
855 Changes the number of channels used only for other purposes
856 e.g. link interrupts or SR-IOV co-ordination.
857
858 combined N
859 Changes the number of multi-purpose channels.
860
861 -m --dump-module-eeprom --module-info
862 Retrieves and if possible decodes the EEPROM from plugin mod‐
863 ules, e.g SFP+, QSFP. If the driver and module support it, the
864 optical diagnostic information is also read and decoded. When
865 either one of page, bank or i2c parameters is specified, dumps
866 only of a single page or its portion is allowed. In such a case
867 offset and length parameters are treated relatively to EEPROM
868 page boundaries.
869
870 --show-priv-flags
871 Queries the specified network device for its private flags. The
872 names and meanings of private flags (if any) are defined by each
873 network device driver.
874
875 --set-priv-flags
876 Sets the device's private flags as specified.
877
878 flag on|off Sets the state of the named private flag.
879
880 --show-eee
881 Queries the specified network device for its support of Energy-
882 Efficient Ethernet (according to the IEEE 802.3az specifica‐
883 tions)
884
885 --set-eee
886 Sets the device EEE behaviour.
887
888 eee on|off
889 Enables/disables the device support of EEE.
890
891 tx-lpi on|off
892 Determines whether the device should assert its Tx LPI.
893
894 advertise N
895 Sets the speeds for which the device should advertise EEE
896 capabilities. Values are as for --change advertise
897
898 tx-timer N
899 Sets the amount of time the device should stay in idle mode
900 prior to asserting its Tx LPI (in microseconds). This has
901 meaning only when Tx LPI is enabled.
902
903 --set-phy-tunable
904 Sets the PHY tunable parameters.
905
906 downshift on|off
907 Specifies whether downshift should be enabled.
908
909 count N
910 Sets the PHY downshift re-tries count.
911
912 fast-link-down on|off
913 Specifies whether Fast Link Down should be enabled and time
914 until link down (if supported).
915
916 msecs N
917 Sets the period after which the link is reported as down. Note that the PHY may choose
918 the closest supported value. Only on reading back the tunable do you get the actual value.
919
920 energy-detect-power-down on|off
921 Specifies whether Energy Detect Power Down (EDPD) should be
922 enabled (if supported). This will put the RX and TX circuit
923 blocks into a low power mode, and the PHY will wake up peri‐
924 odically to send link pulses to avoid any lock-up situation
925 with a peer PHY that may also have EDPD enabled. By default,
926 this setting will also enable the periodic transmission of
927 TX pulses.
928
929 msecs N
930 Some PHYs support configuration of the wake-up interval to send TX pulses.
931 This setting allows the control of this interval, and 0 disables TX pulses
932 if the PHY supports this. Disabling TX pulses can create a lock-up situation
933 where neither of the PHYs wakes the other one. If unspecified the default
934 value (in milliseconds) will be used by the PHY.
935
936
937 --get-phy-tunable
938 Gets the PHY tunable parameters.
939
940 downshift
941 For operation in cabling environments that are incompatible
942 with 1000BASE-T, PHY device provides an automatic link speed
943 downshift operation. Link speed downshift after N failed
944 1000BASE-T auto-negotiation attempts. Downshift is useful
945 where cable does not have the 4 pairs instance.
946
947 Gets the PHY downshift count/status.
948
949 fast-link-down
950 Depending on the mode it may take 0.5s - 1s until a broken
951 link is reported as down. In certain use cases a link-down
952 event needs to be reported as soon as possible. Some PHYs
953 support a Fast Link Down Feature and may allow configuration
954 of the delay before a broken link is reported as being down.
955
956 Gets the PHY Fast Link Down status / period.
957
958 energy-detect-power-down
959 Gets the current configured setting for Energy Detect Power
960 Down (if supported).
961
962
963 --get-tunable
964 Get the tunable parameters.
965
966 rx-copybreak
967 Get the current rx copybreak value in bytes.
968
969 tx-copybreak
970 Get the current tx copybreak value in bytes.
971
972 tx-buf-size
973 Get the current tx copybreak buffer size in bytes.
974
975 pfc-prevention-tout
976 Get the current pfc prevention timeout value in msecs.
977
978 --set-tunable
979 Set driver's tunable parameters.
980
981 rx-copybreak N
982 Set the rx copybreak value in bytes.
983
984 tx-copybreak N
985 Set the tx copybreak value in bytes.
986
987 tx-buf-size N
988 Set the tx copybreak buffer size in bytes.
989
990 pfc-prevention-tout N
991 Set pfc prevention timeout in msecs. Value of 0 means dis‐
992 able and 65535 means auto.
993
994 --reset
995 Reset hardware components specified by flags and components
996 listed below
997
998 flags N
999 Resets the components based on direct flags mask
1000
1001 mgmt Management processor
1002
1003 irq Interrupt requester
1004
1005 dma DMA engine
1006
1007 filter Filtering/flow direction
1008
1009 offload
1010 Protocol offload
1011
1012 mac Media access controller
1013
1014 phy Transceiver/PHY
1015
1016 ram RAM shared between multiple components ap Application Pro‐
1017 cessor
1018
1019 dedicated
1020 All components dedicated to this interface
1021
1022 all All components used by this interface, even if shared
1023
1024 --show-fec
1025 Queries the specified network device for its support of Forward
1026 Error Correction.
1027
1028 --set-fec
1029 Configures Forward Error Correction for the specified network
1030 device.
1031
1032 Forward Error Correction modes selected by a user are expected
1033 to be persisted after any hotplug events. If a module is swapped
1034 that does not support the current FEC mode, the driver or
1035 firmware must take the link down administratively and report the
1036 problem in the system logs for users to correct.
1037
1038 encoding auto|off|rs|baser|llrs [...]
1039
1040 Sets the FEC encoding for the device. Combinations of op‐
1041 tions are specified as e.g. encoding auto rs ; the seman‐
1042 tics of such combinations vary between drivers.
1043
1044 auto Use the driver's default encoding
1045 off Turn off FEC
1046 RS Force RS-FEC encoding
1047 BaseR Force BaseR encoding
1048 LLRS Force LLRS-FEC encoding
1049
1050 -Q|--per-queue
1051 Applies provided sub command to specific queues.
1052
1053 queue_mask %x
1054 Sets the specific queues which the sub command is applied
1055 to. If queue_mask is not set, the sub command will be ap‐
1056 plied to all queues.
1057
1058 sub_command
1059 Sub command to apply. The supported sub commands include
1060 --show-coalesce and --coalesce.
1061
1062 --cable-test
1063 Perform a cable test and report the results. What results are
1064 returned depends on the capabilities of the network interface.
1065 Typically open pairs and shorted pairs can be reported, along
1066 with pairs being O.K. When a fault is detected the approximate
1067 distance to the fault may be reported.
1068
1069 --cable-test-tdr
1070 Perform a cable test and report the raw Time Domain Reflectome‐
1071 ter data. A pulse is sent down a cable pair and the amplitude
1072 of the reflection, for a given distance, is reported. A break in
1073 the cable returns a big reflection. Minor damage to the cable
1074 returns a small reflection. If the cable is shorted, the ampli‐
1075 tude of the reflection can be negative. By default, data is re‐
1076 turned for lengths between 0 and 150m at 1m steps, for all
1077 pairs. However parameters can be passed to restrict the collec‐
1078 tion of data. It should be noted, that the interface will round
1079 the distances to whatever granularity is actually implemented.
1080 This is often 0.8 of a meter. The results should include the ac‐
1081 tual rounded first and last distance and step size.
1082
1083 first N
1084 Distance along the cable, in meters, where the first mea‐
1085 surement should be made.
1086
1087 last N
1088 Distance along the cable, in meters, where the last measure‐
1089 ment should be made.
1090
1091 step N
1092 Distance, in meters, between each measurement.
1093
1094 pair N
1095 Which pair should be measured. Typically a cable has 4
1096 pairs. 0 = Pair A, 1 = Pair B, ...
1097
1098 --monitor
1099 Listens to netlink notification and displays them.
1100
1101 command
1102 If argument matching a command is used, ethtool only shows
1103 notifications of this type. Without such argument or with
1104 --all, all notification types are shown.
1105
1106 devname
1107 If a device name is used as argument, only notification for
1108 this device are shown. Default is to show notifications for
1109 all devices.
1110
1111 --show-tunnels
1112 Show tunnel-related device capabilities and state. List UDP
1113 ports kernel has programmed the device to parse as VxLAN, or
1114 GENEVE tunnels.
1115
1116 --show-module
1117 Show the transceiver module's parameters.
1118
1119 --set-module
1120 Set the transceiver module's parameters.
1121
1122 power-mode-policy high|auto
1123 Set the power mode policy for the module. When set to high,
1124 the module always operates at high power mode. When set to
1125 auto, the module is transitioned by the host to high power
1126 mode when the first port using it is put administratively up
1127 and to low power mode when the last port using it is put ad‐
1128 ministratively down. The power mode policy can be set before
1129 a module is plugged-in.
1130
1131 --get-plca-cfg
1132 Show the current PLCA parameters for the given interface.
1133
1134 --set-plca-cfg
1135 Change the PLCA settings for the given interface.
1136
1137 enable on|off
1138 Enables or disables the PLCA function. When the PLCA RS is
1139 disabled (default), the PHY operates in plain CSMA/CD mode.
1140 To enable PLCA, the PHY must be assigned a unique plca-id
1141 other than 255. This one can be configured concurrently with
1142 the enable parameter. The enable parameter maps to IEEE
1143 802.3cg-2019 clause 30.16.1.1.1 (aPLCAAdminState) and clause
1144 30.16.1.2.1 (acPLCAAdminControl).
1145
1146 node-id N
1147 The unique node identifier in the range [0 .. 255]. Node ID
1148 0 is reserved for the coordinator node, the one generating
1149 the BEACON signal. There must be exactly one coordinator on
1150 a PLCA network. Setting the node ID to 255 (default) dis‐
1151 ables the node. This parameter maps to IEEE 802.3cg-2019
1152 clause 30.16.1.1.4 (aPLCALocalNodeID).
1153
1154 node-cnt N
1155 The node-cnt [1 .. 255] should be set after the maximum num‐
1156 ber of nodes that can be plugged to the multi-drop network.
1157 This parameter regulates the minimum length of the PLCA cy‐
1158 cle. Therefore, it is only meaningful for the coordinator
1159 node (nod-id = 0). Setting this parameter on a follower node
1160 has no effect. The node-cnt parameter maps to IEEE
1161 802.3cg-2019 clause 30.16.1.1.3 (aPLCANodeCount).
1162
1163 to-tmr N
1164 The TO timer parameter sets the value of the transmit oppor‐
1165 tunity timer in bit-times, and shall be set equal across all
1166 the nodes sharing the same medium for PLCA to work. The de‐
1167 fault value of 32 is enough to cover a link of roughly 50
1168 mt. This parameter maps to IEEE 802.3cg-2019 clause
1169 30.16.1.1.5 (aPLCATransmitOpportunityTimer).
1170
1171 burst-cnt N
1172 The burst-cnt parameter [0 .. 255] indicates the extra num‐
1173 ber of packets that the node is allowed to send during a
1174 single transmit opportunity. By default, this attribute is
1175 0, meaning that the node can send a sigle frame per TO. When
1176 greater than 0, the PLCA RS keeps the TO after any transmis‐
1177 sion, waiting for the MAC to send a new frame for up to
1178 burst-tmr BTs. This can only happen a number of times per
1179 PLCA cycle up to the value of this parameter. After that,
1180 the burst is over and the normal counting of TOs resumes.
1181 This parameter maps to IEEE 802.3cg-2019 clause 30.16.1.1.6
1182 (aPLCAMaxBurstCount).
1183
1184 burst-tmr N
1185 The burst-tmr parameter [0 .. 255] sets how many bit-times
1186 the PLCA RS waits for the MAC to initiate a new transmission
1187 when burst-cnt is greater than 0. If the MAC fails to send a
1188 new frame within this time, the burst ends and the counting
1189 of TOs resumes. Otherwise, the new frame is sent as part of
1190 the current burst. This parameter maps to IEEE 802.3cg-2019
1191 clause 30.16.1.1.7 (aPLCABurstTimer). The value of burst-tmr
1192 should be set greater than the Inter-Frame-Gap (IFG) time of
1193 the MAC (plus some margin) for PLCA burst mode to work as
1194 intended.
1195
1196 --get-plca-status
1197 Show the current PLCA status for the given interface. If on, the
1198 PHY is successfully receiving or generating the BEACON signal.
1199 If off, the PLCA function is temporarily disabled and the PHY is
1200 operating in plain CSMA/CD mode.
1201
1202 --show-mm
1203 Show the MAC Merge layer state. The ethtool argument -I --in‐
1204 clude-statistics can be used with this command, and MAC Merge
1205 layer statistics counters will also be retrieved.
1206
1207 pmac-enabled
1208 Shows whether the pMAC is enabled and capable of receiving
1209 traffic and SMD-V frames (and responding to them with SMD-R
1210 replies).
1211
1212 tx-enabled
1213 Shows whether transmission on the pMAC is administratively
1214 enabled.
1215
1216 tx-active
1217 Shows whether transmission on the pMAC is active (verifica‐
1218 tion is either successful, or was disabled).
1219
1220 tx-min-frag-size
1221 Shows the minimum size (in octets) of transmitted non-final
1222 fragments which can be received by the link partner. Corre‐
1223 sponds to the standard addFragSize variable using the formu‐
1224 la:
1225
1226 tx-min-frag-size = 64 * (1 + addFragSize) - 4
1227
1228 rx-min-frag-size
1229 Shows the minimum size (in octets) of non-final fragments
1230 which the local device supports receiving.
1231
1232 verify-enabled
1233 Shows whether the verification state machine is enabled.
1234 This process, if successful, ensures that preemptible frames
1235 transmitted by the local device will not be dropped as error
1236 frames by the link partner.
1237
1238 verify-time
1239 Shows the interval in ms between verification attempts, rep‐
1240 resented as an integer between 1 and 128 ms. The standard
1241 defines a fixed number of verification attempts (verifyLim‐
1242 it) before failing the verification process.
1243
1244 max-verify-time
1245 Shows the maximum value for verify-time accepted by the lo‐
1246 cal device, which may be less than 128 ms.
1247
1248 verify-status
1249 Shows the current state of the verification state machine of
1250 the local device. Values can be INITIAL, VERIFYING, SUC‐
1251 CEEDED, FAILED or DISABLED.
1252
1253
1254 --set-mm
1255 Set the MAC Merge layer parameters.
1256
1257 pmac-enabled on|off
1258 Enable reception for the pMAC.
1259
1260 tx-enabled on|off
1261 Administatively enable transmission for the pMAC.
1262
1263 tx-min-frag-size N
1264 Set the minimum size (in octets) of transmitted non-final
1265 fragments which can be received by the link partner.
1266
1267 verify-enabled on|off
1268 Enable or disable the verification state machine.
1269
1270 verify-time N
1271 Set the interval in ms between verification attempts.
1272
1273
1274 --show-pse
1275 Show the current Power Sourcing Equipment (PSE) status for the
1276 given interface.
1277
1278 podl-pse-admin-state
1279 This attribute indicates the operational status of PoDL PSE
1280 functions, which can be modified using the podl-pse-admin-
1281 control parameter. It corresponds to IEEE 802.3-2018
1282 30.15.1.1.2 (aPoDLPSEAdminState), with potential values be‐
1283 ing enabled, disabled
1284
1285 podl-pse-power-detection-status
1286 This attribute indicates the power detection status of the
1287 PoDL PSE. The status depend on internal PSE state machine
1288 and automatic PD classification support. It corresponds to
1289 IEEE 802.3-2018 30.15.1.1.3 (aPoDLPSEPowerDetectionStatus)
1290 with potential values being disabled, searching, delivering
1291 power, sleep, idle, error
1292
1293
1294 --set-pse
1295 Set Power Sourcing Equipment (PSE) parameters.
1296
1297 podl-pse-admin-control enable|disable
1298 This parameter manages PoDL PSE Admin operations in accor‐
1299 dance with the IEEE 802.3-2018 30.15.1.2.1 (acPoDLPSEAdmin‐
1300 Control) specification.
1301
1302
1304 Not supported (in part or whole) on all network drivers.
1305
1307 ethtool was written by David Miller.
1308
1309 Modifications by Jeff Garzik, Tim Hockin, Jakub Jelinek, Andre Majorel,
1310 Eli Kupermann, Scott Feldman, Andi Kleen, Alexander Duyck, Sucheta
1311 Chakraborty, Jesse Brandeburg, Ben Hutchings, Scott Branden.
1312
1314 ethtool is available from
1315 ⟨http://www.kernel.org/pub/software/network/ethtool/⟩
1316
1317
1318
1319Ethtool version 6.6 November 2023 ETHTOOL(8)