Jump to content

Router на FreeBSD и flapping between port

kinder
 Share

Recommended Posts

kinder

kinder

Posted
Posted (edited)

Всем привет

 

Прошу помощи в решении проблемы.

Имеется сеть. В сети Стоит 3 сервера

Два IBM 3250 m3 и один HP DL 160. Стоит freebsd 7.4, MPD5, quagga

На обоих IBM стоят Intel Pro Dual на Dl 160 родные сетевушки.

 

Каждый сервер подключен 2-мя ногами к catalist 3750E.

На одной сетевой мир. На второй локальные вланы.

 

 

С недавнего времени стали падать интерфейсы на IBM'ах. Точнее линки горят, но пакеты не ходят.

В логах серверов нет нечего. На кошке

Nov 28 20:48:21: %SW_MATM-4-MACFLAP_NOTIF: Host 70ca.9b0b.a810 in vlan 328 is flapping between port Gi1/0/5 and port Te1/0/1

Nov 28 20:48:21: %SW_MATM-4-MACFLAP_NOTIF: Host 70ca.9b0b.a810 in vlan 324 is flapping between port Gi1/0/5 and port Te1/0/1

Nov 28 20:48:29: %SW_MATM-4-MACFLAP_NOTIF: Host 70ca.9b0b.a810 in vlan 328 is flapping between port Gi1/0/5 and port Te1/0/1

Nov 28 20:48:38: %SW_MATM-4-MACFLAP_NOTIF: Host 0021.5e68.2105 in vlan 324 is flapping between port Gi1/0/5 and port Te1/0/1

Nov 28 20:48:39: %SW_MATM-4-MACFLAP_NOTIF: Host 0021.5e68.2105 in vlan 319 is flapping between port Gi1/0/5 and port Te1/0/1

 

Te1/0/1 - смотрит в сеть

Gi1/0/5 - на интерфейс браса с локальными vlan'ами

 

Проблема уходит после выключения и включения интерфейса.

 

Прошу помощи как решить вопрос с падениями интерфейсов на IBM. С DL проблем нет совсем.

В гугле не нашел не чего полезного.

Буду рад любой ссылке или совету.

Edited by kinder
kinder

kinder

Posted
  • Author
Posted

Немного информации

vmstat -z

ITEM SIZE LIMIT USED FREE REQUESTS FAILURES

 

UMA Kegs: 216, 0, 88, 14, 89, 0

UMA Zones: 280, 0, 88, 3, 89, 0

UMA Slabs: 128, 0, 32279, 433, 296538, 0

UMA RCntSlabs: 128, 0, 3571, 25, 3571, 0

UMA Hash: 256, 0, 4, 11, 8, 0

16 Bucket: 152, 0, 139, 11, 139, 0

32 Bucket: 280, 0, 148, 6, 148, 0

64 Bucket: 536, 0, 169, 6, 193, 216

128 Bucket: 1048, 0, 3318, 0, 84776, 805

VM OBJECT: 216, 0, 59783, 3343, 231608506, 0

MAP: 256, 0, 7, 23, 7, 0

KMAP ENTRY: 112, 276441, 74, 982, 33724233, 0

MAP ENTRY: 112, 0, 2518, 2201, 447727472, 0

DP fakepg: 120, 0, 0, 0, 0, 0

SG fakepg: 120, 0, 0, 0, 0, 0

mt_zone: 1032, 0, 261, 48, 261, 0

16: 16, 0, 7152, 1584, 557393965, 0

32: 32, 0, 18007, 3607, 46496369412, 0

64: 64, 0, 22737, 2855, 446719773, 0

128: 128, 0, 150515, 23804, 159320764, 0

256: 256, 0, 29652, 5163, 47496934, 0

512: 512, 0, 13454, 2478, 27140155, 0

1024: 1024, 0, 5079, 1541, 117211830, 0

2048: 2048, 0, 2533, 801, 319183, 0

4096: 4096, 0, 9877, 2031, 35448653, 0

Files: 128, 0, 240, 1645, 413660359, 0

TURNSTILE: 152, 0, 1945, 95, 1945, 0

umtx pi: 96, 0, 0, 0, 0, 0

PROC: 1160, 0, 87, 189, 14269872, 0

THREAD: 920, 0, 291, 1653, 20691095, 0

UPCALL: 88, 0, 0, 0, 0, 0

SLEEPQUEUE: 64, 0, 1945, 183, 1945, 0

VMSPACE: 432, 0, 30, 177, 14269827, 0

cpuset: 72, 0, 2, 98, 2, 0

audit_record: 992, 0, 0, 0, 0, 0

mbuf_packet: 256, 0, 61, 1603, 244829707, 0

mbuf: 256, 0, 3049, 4377, 212213265295, 0

mbuf_cluster: 2048, 25600, 4698, 2236, 83659790875, 0

mbuf_jumbo_pagesize: 4096, 12800, 0, 104, 73555, 0

mbuf_jumbo_9k: 9216, 6400, 0, 0, 0, 0

mbuf_jumbo_16k: 16384, 3200, 0, 0, 0, 0

mbuf_ext_refcnt: 4, 0, 0, 0, 0, 0

ACL UMA zone: 388, 0, 0, 0, 0, 0

g_bio: 216, 0, 0, 14580, 2137383, 0

ata_request: 312, 0, 0, 24, 31, 0

ata_composite: 352, 0, 0, 0, 0, 0

VNODE: 504, 0, 108733, 3659, 4031313, 0

VNODEPOLL: 128, 0, 1, 57, 1, 0

S VFS Cache: 104, 0, 124750, 3338, 4060428, 0

L VFS Cache: 327, 0, 1163, 4609, 120921, 0

NAMEI: 1024, 0, 0, 112, 91552282, 0

DIRHASH: 1024, 0, 1716, 60, 1742, 0

NFSMOUNT: 656, 0, 0, 0, 0, 0

NFSNODE: 704, 0, 0, 0, 0, 0

pipe: 744, 0, 7, 98, 11573033, 0

ksiginfo: 112, 0, 228, 828, 228, 0

itimer: 360, 0, 0, 20, 1, 0

KNOTE: 120, 0, 0, 372, 147570, 0

socket: 720, 25600, 164, 1636, 339378919, 0

ipq: 56, 819, 0, 189, 23, 0

udp_inpcb: 288, 25610, 24, 1627, 335764411, 0

udpcb: 16, 25704, 24, 2160, 335764411, 0

inpcb: 288, 25610, 13, 169, 14605, 0

tcpcb: 728, 25600, 13, 112, 14605, 0

tcptw: 88, 5124, 0, 252, 179, 0

syncache: 128, 15370, 0, 174, 14589, 0

hostcache: 136, 15372, 5, 135, 130, 0

tcpreass: 40, 1680, 0, 420, 7706, 0

sackhole: 32, 0, 0, 202, 16, 0

sctp_ep: 1232, 25602, 0, 0, 0, 0

sctp_asoc: 2208, 40000, 0, 0, 0, 0

sctp_laddr: 48, 80064, 0, 144, 1, 0

sctp_raddr: 584, 80003, 0, 0, 0, 0

sctp_chunk: 144, 400010, 0, 0, 0, 0

sctp_readq: 104, 400032, 0, 0, 0, 0

sctp_stream_msg_out: 96, 400026, 0, 0, 0, 0

sctp_asconf: 40, 400008, 0, 0, 0, 0

sctp_asconf_ack: 48, 400032, 0, 0, 0, 0

ripcb: 288, 25610, 2, 63, 364, 0

unpcb: 248, 25605, 19, 206, 3599320, 0

rtentry: 248, 0, 6819, 891, 867260, 0

SWAPMETA: 288, 116519, 0, 0, 0, 0

Mountpoints: 896, 0, 5, 7, 5, 0

FFS inode: 184, 0, 108691, 3659, 4031150, 0

FFS1 dinode: 128, 0, 0, 0, 0, 0

FFS2 dinode: 256, 0, 108691, 3779, 4031150, 0

IPFW dynamic rule: 120, 0, 0, 0, 0, 0

NetGraph items: 72, 4140, 77, 1453, 9488941436, 0

NetGraph data items: 72, 540, 1, 539, 96411301260, 80079

NetFlow cache: 80, 262170, 43865, 18685, 842937354, 0

 

ifconfig | grep vlan

vlan342: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500

vlan: 342 parent interface: em1

vlan343: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500

vlan: 343 parent interface: em1

vlan344: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500

vlan: 344 parent interface: em1

vlan345: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500

vlan: 345 parent interface: em1

vlan346: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500

vlan: 346 parent interface: em1

vlan347: flags=8843<UP,BROADCAST,RUNNING,SIMPLEX,MULTICAST> metric 0 mtu 1500

vlan: 347 parent interface: em1

 

 

 

Трафик в час пик

bras-02# netstat -w1 -h

input (Total) output

packets errs bytes packets errs bytes colls

396K 0 322M 372K 0 249M 0

473K 0 334M 491K 0 408M 0

472K 0 324M 490K 0 400M 0

453K 0 314M 472K 0 388M 0

457K 0 315M 476K 0 391M 0

464K 0 327M 482K 0 399M 0

459K 0 320M 478K 0 396M 0

477K 0 334M 494K 0 407M 0

477K 0 335M 495K 0 410M 0

Ivan_83

Ivan_83

Posted
Posted
NetGraph data items: 72, 540, 1, 539, 96411301260, 80079

net.graph.maxalloc="65535" # Maximum number of non-data queue items to allocate / limit the damage of a leak

net.graph.maxdata="65535" # Maximum number of data queue items to allocate / limit the damage of a DoS

roysbike

roysbike

Posted
Posted

2 дня полет нормальный!

Пока наблюдаю.

 

Дополнительно провел тюнинг по следующим статьям.

http://dadv.livejournal.com/138951.html

http://dadv.livejournal.com/139170.html

а у вас какие карты стоят? Intel 82576 ? можете показать top -SHPI в пике

kinder

kinder

Posted
  • Author
Posted

last pid: 81596; load averages: 0.58, 0.54, 0.51 up 4+00:14:07 20:46:41

102 processes: 9 running, 77 sleeping, 16 waiting

CPU 0: 16.2% user, 0.0% nice, 5.3% system, 5.3% interrupt, 73.3% idle

CPU 1: 0.4% user, 0.0% nice, 1.1% system, 84.2% interrupt, 14.3% idle

CPU 2: 4.9% user, 0.0% nice, 0.4% system, 65.4% interrupt, 29.3% idle

CPU 3: 2.3% user, 0.0% nice, 0.0% system, 58.6% interrupt, 39.1% idle

Mem: 142M Active, 1198M Inact, 1184M Wired, 144K Cache, 827M Buf, 5343M Free

Swap: 8196M Total, 8196M Free

 

PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU COMMAND

44 root -64 - 0K 16K CPU1 1 73.9H 82.67% irq18: atapci1

14 root 171 ki31 0K 16K RUN 0 70.4H 71.58% idle: cpu0

38 root -68 - 0K 16K CPU2 2 37.3H 65.97% irq259: em1

33 root -68 - 0K 16K CPU3 3 35.5H 61.96% irq256: em0

11 root 171 ki31 0K 16K RUN 3 53.4H 37.99% idle: cpu3

12 root 171 ki31 0K 16K RUN 2 54.0H 31.69% idle: cpu2

4906 root 70 0 24872K 11976K select 3 901:11 22.36% snmpd

13 root 171 ki31 0K 16K RUN 1 20.4H 15.38% idle: cpu1

4843 root 48 0 332M 139M select 0 417:40 7.18% mpd5

4843 root 48 0 332M 139M select 0 0:00 6.69% mpd5

3402 root 48 0 13212K 7136K select 0 31:40 3.86% zebra

40 root -68 - 0K 16K WAIT 1 151:46 3.47% irq260: em1

4843 root 48 0 332M 139M select 3 0:00 2.59% mpd5

35 root -68 - 0K 16K WAIT 0 81:54 2.10% irq257: em0

16 root -32 - 0K 16K WAIT 0 337:29 1.56% swi4: clock sio

roysbike

roysbike

Posted
Posted

last pid: 81596; load averages: 0.58, 0.54, 0.51 up 4+00:14:07 20:46:41

102 processes: 9 running, 77 sleeping, 16 waiting

CPU 0: 16.2% user, 0.0% nice, 5.3% system, 5.3% interrupt, 73.3% idle

CPU 1: 0.4% user, 0.0% nice, 1.1% system, 84.2% interrupt, 14.3% idle

CPU 2: 4.9% user, 0.0% nice, 0.4% system, 65.4% interrupt, 29.3% idle

CPU 3: 2.3% user, 0.0% nice, 0.0% system, 58.6% interrupt, 39.1% idle

Mem: 142M Active, 1198M Inact, 1184M Wired, 144K Cache, 827M Buf, 5343M Free

Swap: 8196M Total, 8196M Free

 

PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU COMMAND

44 root -64 - 0K 16K CPU1 1 73.9H 82.67% irq18: atapci1

14 root 171 ki31 0K 16K RUN 0 70.4H 71.58% idle: cpu0

38 root -68 - 0K 16K CPU2 2 37.3H 65.97% irq259: em1

33 root -68 - 0K 16K CPU3 3 35.5H 61.96% irq256: em0

11 root 171 ki31 0K 16K RUN 3 53.4H 37.99% idle: cpu3

12 root 171 ki31 0K 16K RUN 2 54.0H 31.69% idle: cpu2

4906 root 70 0 24872K 11976K select 3 901:11 22.36% snmpd

13 root 171 ki31 0K 16K RUN 1 20.4H 15.38% idle: cpu1

4843 root 48 0 332M 139M select 0 417:40 7.18% mpd5

4843 root 48 0 332M 139M select 0 0:00 6.69% mpd5

3402 root 48 0 13212K 7136K select 0 31:40 3.86% zebra

40 root -68 - 0K 16K WAIT 1 151:46 3.47% irq260: em1

4843 root 48 0 332M 139M select 3 0:00 2.59% mpd5

35 root -68 - 0K 16K WAIT 0 81:54 2.10% irq257: em0

16 root -32 - 0K 16K WAIT 0 337:29 1.56% swi4: clock sio

не плохо. Видимо проц хороший. У вас em0 uplink?а на em1 вланы и pppoe слушает?

kinder

kinder

Posted
  • Author
Posted

> У вас em0 uplink?а на em1 вланы и pppoe слушает?

Так и есть.

 

 

Железо бралось заведомо для возможности использовать 10G. Но как то не сложилось!

Freebsd не захотела дружить с сетевой 10G.

Скоро начну танцы.

roysbike

roysbike

Posted
Posted (edited)

> У вас em0 uplink?а на em1 вланы и pppoe слушает?

Так и есть.

 

 

Железо бралось заведомо для возможности использовать 10G. Но как то не сложилось!

Freebsd не захотела дружить с сетевой 10G.

Скоро начну танцы.

я заказал карту 10g fiber. на чипе 82599. Но для бордера , за бордером 5 PPPoE cерверов

Edited by roysbike

Join the conversation

You can post now and register later. If you have an account, sign in now to post with your account.

Guest
Reply to this topic...

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
 Share
Go to topic listing
×
×
  • Create New...
На сайте используются файлы cookie и сервисы аналитики для корректной работы форума и улучшения качества обслуживания. Продолжая использовать сайт, вы соглашаетесь с использованием файлов cookie и с Политикой конфиденциальности.