LINUX.ORG.RU
ФорумAdmin

TX packets - откуда errors и overruns в ipconfig?


0

0

# ifconfig eth2
eth2 Link encap:Ethernet HWaddr 00:1d:60:5c:a6:48
inet6 addr: fe80::21d:60ff:fe5c:a648/64 Scope:Link
UP BROADCAST RUNNING MULTICAST MTU:1500 Metric:1
RX packets:93003172 errors:0 dropped:0 overruns:0 frame:0
TX packets:49760447 errors:3893 dropped:0 overruns:3893 carrier:0
collisions:0 txqueuelen:1000
RX bytes:139604364798 (130.0 GiB) TX bytes:3737522728 (3.4 GiB)
Interrupt:19

Пробовал ядро 2.6.29-r2, не помогло. Пробовал менять некоторые настройки net.ipv4.tcp_timestamps, net.ipv4.tcp_window_scaling, net.ipv4.tcp_sack на = 0 - не помогло.

После возникновения ошибок сеть перестает работать, в /var/log/messages ничего не пишется.

После ifconfig eth2 down && ifconfig eth2 up в лог записывается:
# tail /var/log/messages
May 20 23:03:56 basis2 br2: port 1(eth2) entering disabled state
May 20 23:03:56 basis2 eth2: Link speed = 1000Mbps.
May 20 23:03:56 basis2 eth2: setting full duplex, TX flow control, RX flow control.
May 20 23:03:56 basis2 br2: port 1(eth2) entering learning state
May 20 23:03:56 basis2 br2: topology change detected, propagating
May 20 23:03:56 basis2 br2: port 1(eth2) entering forwarding state
May 20 23:04:06 basis2 eth2: no IPv6 routers present

Затем через некоторое время сеть перестает работать опять.

# lspci | grep Eth
04:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL8111/8168B PCI Express Gigabit Ethernet controller (rev 01)
05:00.0 Ethernet controller: Realtek Semiconductor Co., Ltd. RTL-8139/8139C/8139C+ (rev 10)
05:01.0 Ethernet controller: Sundance Technology Inc / IC Plus Corp IP1000 Family Gigabit Ethernet (rev 41)

# uname -r
2.6.26-gentoo-r4

# cat /etc/udev/rules.d/70-persistent-net.rules
# PCI device 0x10ec:0x8168 (r8169)
SUBSYSTEM=="net", ACTION=="add", DRIVERS=="?*", ATTR{address}=="00:1d:7d:04:80:cb", ATTR{type}=="1", KERNEL=="eth*", NAME="eth0"
# PCI device 0x10ec:0x8139 (8139too)
SUBSYSTEM=="net", ACTION=="add", DRIVERS=="?*", ATTR{address}=="00:e0:4c:a9:c3:ca", ATTR{type}=="1", KERNEL=="eth*", NAME="eth1"
# PCI device 0x13f0:0x1023 (Sundance Technology IPG Triple-Speed Ethernet)
SUBSYSTEM=="net", ACTION=="add", DRIVERS=="?*", ATTR{address}=="00:1d:60:5c:a6:48", ATTR{type}=="1", KERNEL=="eth*", NAME="eth2"

# netstat -sovetu | sort -nr
94264802 segments received
64595540 packet headers predicted
50488623 segments send out
203717 DSACKs sent for old packets
108646 packets rejects in established connections because of timestamp
74351 predicted acknowledgments
7776 acknowledgments not containing data payload received
5559 packets collapsed in receive queue due to low socket buffer
2688 delayed acks sent
2569 segments retransmited
2250 packets received
867 packets sent
595 delayed acks further delayed because of locked socket
536 other TCP timeouts
64 DSACKs sent for out of order packets
61 ICMP packets dropped because they were out-of-window
43 congestion windows recovered without slow start by DSACK
36 passive connection openings
29 packets directly queued to recvmsg prequeue.
19 retransmits in slow start
10 connection resets received
9 TCP sockets finished time wait in fast timer
7 DSACKs received
4 resets sent
4 connections established
3 packets to unknown port received.
3 packets pruned from receive queue because of socket buffer overrun
2 timeouts after SACK recovery
2 TCP data loss events
2 failed connection attempts
2 connections reset due to early user close
1 times recovered from packet loss by selective acknowledgements
1 SACK retransmits failed
1 resets received for embryonic SYN_RECV sockets
1 fast retransmits
1 connections aborted due to timeout
1 congestion windows recovered without slow start after partial ack
1 active connections openings
UdpLite:
Udp:
TcpExt:
TCPDSACKIgnoredNoUndo: 5
Tcp:
Quick ack mode was activated 203717 times
OutType8: 222
OutType3: 647
OutType0: 1490
IpExt:
InType8: 1490
InType3: 644
InType0: 3
InBcastPkts: 2972
IcmpMsg:
0 packet receive errors
0 bad segments received.

# cat /proc/net/dev
Inter-| Receive | Transmit
face |bytes packets errs drop fifo frame compressed multicast|bytes packets errs drop fifo colls carrier compressed
eth2:142585350617 95015168 0 0 0 0 0 1711834 3832754539 50865128 3985 0 3985 0 0 0
br2:141249358361 95011218 0 0 0 0 0 23827 3839579640 50926628 0 0 0 0 0 0

# cat /proc/sys/net/core/wmem_max
131071
# cat /proc/sys/net/core/rmem_max
131071

# sysctl -a | fgrep tcp
error: "Invalid argument" reading key "fs.binfmt_misc.register"
error: permission denied on key 'net.ipv4.route.flush'
fs.nfs.nlm_tcpport = 0
net.ipv4.tcp_timestamps = 1
net.ipv4.tcp_window_scaling = 1
net.ipv4.tcp_sack = 1
net.ipv4.tcp_retrans_collapse = 1
net.ipv4.tcp_syn_retries = 5
net.ipv4.tcp_synack_retries = 5
net.ipv4.tcp_max_orphans = 65536
net.ipv4.tcp_max_tw_buckets = 180000
net.ipv4.tcp_keepalive_time = 7200
net.ipv4.tcp_keepalive_probes = 9
net.ipv4.tcp_keepalive_intvl = 75
net.ipv4.tcp_retries1 = 3
net.ipv4.tcp_retries2 = 15
net.ipv4.tcp_fin_timeout = 60
net.ipv4.tcp_tw_recycle = 0
net.ipv4.tcp_abort_on_overflow = 0
net.ipv4.tcp_stdurg = 0
net.ipv4.tcp_rfc1337 = 0
net.ipv4.tcp_max_syn_backlog = 1024
net.ipv4.tcp_orphan_retries = 0
net.ipv4.tcp_fack = 1
net.ipv4.tcp_reordering = 3
net.ipv4.tcp_ecn = 0
net.ipv4.tcp_dsack = 1
net.ipv4.tcp_mem = 766560 1022080 1533120
net.ipv4.tcp_wmem = 4096 655360 6553600
net.ipv4.tcp_rmem = 8192 873800 8738000
net.ipv4.tcp_app_win = 31
net.ipv4.tcp_adv_win_scale = 2
net.ipv4.tcp_tw_reuse = 0
net.ipv4.tcp_frto = 2
net.ipv4.tcp_frto_response = 0
net.ipv4.tcp_low_latency = 0
net.ipv4.tcp_no_metrics_save = 1
net.ipv4.tcp_moderate_rcvbuf = 1
net.ipv4.tcp_tso_win_divisor = 3
net.ipv4.tcp_congestion_control = reno
net.ipv4.tcp_abc = 0
net.ipv4.tcp_mtu_probing = 0
net.ipv4.tcp_base_mss = 512
net.ipv4.tcp_workaround_signed_windows = 0
net.ipv4.tcp_slow_start_after_idle = 1
net.ipv4.tcp_available_congestion_control = reno cubic bic westwood highspeed hybla htcp vegas veno scalable lp yeah illinois
net.ipv4.tcp_allowed_congestion_control = reno cubic
net.ipv4.tcp_max_ssthresh = 0
error: permission denied on key 'net.ipv6.route.flush'
sunrpc.transports = tcp 1048576
sunrpc.tcp_slot_table_entries = 16

у тебя там софтовый свитч чтоли? br интерфейсы есть?

May 20 23:03:56 basis2 br2: port 1(eth2) entering learning state
May 20 23:03:56 basis2 br2: topology change detected, propagating
May 20 23:03:56 basis2 br2: port 1(eth2) entering forwarding state

этож stp в чистом виде.
я не очень знаком с внутренностями linux реализации stp, но теоретически при state отличном от форвардинг, дропнутые фреймы могут писаться в TX packets:49760447 errors:3893 dropped:0 overruns:3893 carrier:0

тем более, что дело повторяется на двух независимых сетевых.

chocholl ★★
()
Ответ на: комментарий от ArsenShnurkov

тогда пинать другой конец этого проводка, куда он там включен

hizel ★★★★★
()
Вы не можете добавлять комментарии в эту тему. Тема перемещена в архив.