em(4) dropping packets

From: Przemyslaw Frasunek <venglin_at_freebsd.lublin.pl>
Date: Sun, 13 Jun 2004 15:30:28 +0200
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Hello,

I'm running 5.2.1-RELEASE on two heavly loaded USENET servers equipped with
Intel PRO/1000 on-board NICs:

em0: <Intel(R) PRO/1000 Network Connection, Version - 1.7.19> port
0xd800-0xd83f mem 0xfe8c0000-0xfe8dffff irq 28 at device 1.0 on pci3

Recently, on both servers I've noticed increasing number of input errors on
netstat -i:

Name    Mtu Network       Address              Ipkts Ierrs    Opkts Oerrs  Coll
em0    1500 <Link#1>      00:30:48:70:43:24 531562478 4362496 782338592
 0   0

NIC stats shows, that errors are related to "receive no buffers", but
netstat -m doesn't show any mbuf or mbuf cluster exhaustion.

em0: Excessive collisions = 0
em0: Symbol errors = 0
em0: Sequence errors = 0
em0: Defer count = 0
em0: Missed Packets = 85980
em0: Receive No Buffers = 4274612
em0: Receive length errors = 0
em0: Receive errors = 0
em0: Crc errors = 0
em0: Alignment errors = 0
em0: Carrier extension errors = 0
em0: XON Rcvd = 0
em0: XON Xmtd = 0
em0: XOFF Rcvd = 0
em0: XOFF Xmtd = 0
em0: Good Packets Rcvd = 531193051
em0: Good Packets Xmtd = 781747213

mbuf usage:
        GEN cache:      27/4032 (in use/in pool)
        CPU #0 cache:   3109/3232 (in use/in pool)
        CPU #1 cache:   34/512 (in use/in pool)
        CPU #2 cache:   21/512 (in use/in pool)
        CPU #3 cache:   11/512 (in use/in pool)
        Total:          3202/8800 (in use/in pool)
        Mbuf cache high watermark: 512
        Maximum possible: 51200
        Allocated mbuf types:
          3202 mbufs allocated to data
        17% of mbuf map consumed
mbuf cluster usage:
        GEN cache:      25/3864 (in use/in pool)
        CPU #0 cache:   3101/3176 (in use/in pool)
        CPU #1 cache:   37/160 (in use/in pool)
        CPU #2 cache:   23/128 (in use/in pool)
        CPU #3 cache:   11/128 (in use/in pool)
        Total:          3197/7456 (in use/in pool)
        Cluster cache high watermark: 128
        Maximum possible: 25600
        29% of cluster map consumed
17112 KBytes of wired memory reserved (42% in use)
0 requests for memory denied
0 requests for memory delayed
0 calls to protocol drain routines

If you have any ideas I'd really appreciate it.

- --
* Fido: 2:480/124 ** WWW: http://www.frasunek.com/ ** NICHDL: PMF9-RIPE *
* JID: venglin_at_jabber.atman.pl ** PGP ID: 2578FCAD ** HAM-RADIO: SQ8JIV *
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)
Comment: Using GnuPG with Thunderbird - http://enigmail.mozdev.org

iD8DBQFAzFbzkxEnBiV4/K0RAmN4AKCC12t/q/O84m+/4ejwv6QWlOJo8QCgjNZs
DuBbDYgvja0Dupzl6ZoL2cI=
=4OZI
-----END PGP SIGNATURE-----
Received on Sun Jun 13 2004 - 11:31:41 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:37:57 UTC