More on: No buffer space available

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1


'k, here's a bit more data, see if something jumps out at anyone ... first, a
bit of a timeline ...

Tonight, after ~75hrs uptime, I got an SMS, which is what generally indicates
the problem has begun ... the SMS is a result of a cron job running on the
machine that pings another server on the same network ... if it can't ping it,
it sends me an SMS (ie. the other server is down) ... the neat thing is that
I'm also sent one when it comes back up again ... normally, I get the 'down'
before I get the 'up' ... when this problem starts to manifest itself, I get
the 'up' message, followed a bit later by the 'down' ... the reason: since the
network is down (it can't ping), it also can't send out the 'down' message, so
it queues it up ... as soon as it comes back up again, mail works again, so the
'up' goes out before queue is re-processed ...

That said ...

When I got my first SMS, I logged in and ran the two commands Robert suggested:


142/968/1110 mbufs in use (current/cache/total)
136/552/688/25600 mbuf clusters in use (current/cache/total/max)
136/388 mbuf+clusters out of packet secondary zone in use (current/cache)
0/0/0/0 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/0 9k jumbo clusters in use (current/cache/total/max)
0/0/0/0 16k jumbo clusters in use (current/cache/total/max)
307K/1346K/1653K bytes allocated to network (current/cache/total)
0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 requests for jumbo clusters denied (4k/9k/16k)
0/38/6656 sfbufs in use (current/peak/max)
0 requests for sfbufs denied
0 requests for sfbufs delayed
396 requests for I/O initiated by sendfile
713 calls to protocol drain routines

Now, just over 4 hours later (I'm just about to reboot):

421/914/1335 mbufs in use (current/cache/total)
233/617/850/25600 mbuf clusters in use (current/cache/total/max)
233/361 mbuf+clusters out of packet secondary zone in use (current/cache)
0/0/0/0 4k (page size) jumbo clusters in use (current/cache/total/max)
0/0/0/0 9k jumbo clusters in use (current/cache/total/max)
0/0/0/0 16k jumbo clusters in use (current/cache/total/max)
571K/1462K/2033K bytes allocated to network (current/cache/total)
0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 requests for jumbo clusters denied (4k/9k/16k)
0/38/6656 sfbufs in use (current/peak/max)
0 requests for sfbufs denied
0 requests for sfbufs delayed
406 requests for I/O initiated by sendfile
733 calls to protocol drain routines

Now, the vmstat -z is a wee bit longer:

ITEM SIZE LIMIT USED FREE REQUESTS FAILURES

UMA Kegs: 140, 0, 64, 8, 64, 0
UMA Zones: 480, 0, 64, 0, 64, 0
UMA Slabs: 64, 0, 3069, 1238, 128266, 0
UMA RCntSlabs: 104, 0, 344, 100, 14486, 0
UMA Hash: 128, 0, 4, 26, 7, 0
16 Bucket: 76, 0, 15, 35, 70, 0
32 Bucket: 140, 0, 22, 34, 87, 0
64 Bucket: 268, 0, 25, 59, 220, 9
128 Bucket: 524, 0, 2975, 147, 80119, 1572874
VM OBJECT: 132, 0, 74837, 29795, 94095430, 0
MAP: 192, 0, 7, 13, 7, 0
KMAP ENTRY: 68, 57344, 747, 877, 623962, 0
MAP ENTRY: 68, 0, 89827, 13941, 192935836, 0
PV ENTRY: 24, 2245615, 1255065, 247860, 3181072639,
0
DP fakepg: 72, 0, 0, 0, 0, 0
mt_zone: 1024, 0, 134, 126, 134, 0
16: 16, 0, 8483, 449, 19117061, 0
32: 32, 0, 4673, 3915, 8407030, 0
64: 64, 0, 8889, 3029, 24622501, 0
128: 128, 0, 19660, 3620, 88038870, 0
256: 256, 0, 3891, 2319, 9037915, 0
512: 512, 0, 847, 993, 1874043, 0
1024: 1024, 0, 631, 357, 2814842, 0
2048: 2048, 0, 293, 381, 812570, 0
4096: 4096, 0, 1130, 439, 4342201, 0
Files: 72, 0, 11119, 3191, 72134326, 0
PROC: 536, 0, 1073, 971, 2510920, 0
THREAD: 376, 0, 2188, 372, 352225, 0
KSEGRP: 88, 0, 2137, 383, 32084, 0
UPCALL: 44, 0, 119, 349, 30104, 0
VMSPACE: 296, 0, 1034, 812, 2510845, 0
mbuf_packet: 256, 0, 142, 382, 33140922, 0
mbuf: 256, 0, 44, 542, 65939839, 0
mbuf_cluster: 2048, 25600, 524, 164, 345305, 0
mbuf_jumbo_pagesize: 4096, 0, 0, 0, 0, 0
mbuf_jumbo_9k: 9216, 0, 0, 0, 0, 0
mbuf_jumbo_16k: 16384, 0, 0, 0, 0, 0
ACL UMA zone: 388, 0, 0, 0, 0, 0
g_bio: 132, 0, 0, 4205, 87153652, 0
VNODE: 272, 0, 71264, 22158, 1241560352,
0
VNODEPOLL: 76, 0, 0, 100, 3, 0
S VFS Cache: 68, 0, 73121, 29135, 1248334482,
0
L VFS Cache: 291, 0, 124, 1085, 682683, 0
NAMEI: 1024, 0, 0, 304, 1434961352,
0
DIRHASH: 1024, 0, 1810, 258, 18000204, 0
PIPE: 408, 0, 1981, 602, 1091976, 0
KNOTE: 68, 0, 32, 360, 3972127, 0
socket: 356, 12331, 12271, 60, 8439626, 1141
unpcb: 144, 12339, 11561, 373, 5337418, 0
ipq: 32, 904, 0, 226, 2, 0
udpcb: 180, 12342, 74, 146, 2173707, 0
inpcb: 180, 12342, 678, 1478, 927361, 0
tcpcb: 464, 12328, 619, 717, 927361, 0
tcptw: 48, 2496, 59, 1501, 256613, 0
syncache: 100, 15366, 0, 195, 676224, 0
hostcache: 76, 15400, 512, 688, 34850, 0
tcpreass: 20, 1690, 0, 507, 53830, 0
sackhole: 20, 0, 0, 507, 20912, 0
ripcb: 180, 12342, 0, 88, 1127, 0
rtentry: 132, 0, 203, 319, 6656, 0
g_stripe_zone: 131072, 100, 0, 0, 0, 0
SWAPMETA: 276, 121576, 957, 429, 17641, 0
Mountpoints: 664, 0, 197, 19, 200, 0
FFS inode: 132, 0, 70901, 17491, 1239034732,
0
FFS1 dinode: 128, 0, 0, 0, 0, 0
FFS2 dinode: 256, 0, 70901, 7924, 1239034732,
0

If the '4 hour later' version is of any use, please ask, I did save a copy
before rebooting ...

Does this provide anything? Is there something else I should do/try?

Thanks ...


- ----
Marc G. Fournier Hub.Org Networking Services (http://www.hub.org)
Email . scrappy@xxxxxxx MSN . scrappy@xxxxxxx
Yahoo . yscrappy Skype: hub.org ICQ . 7615664
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.5 (FreeBSD)

iD8DBQFGDHfM4QvfyHIvDvMRAhZlAJ4sR9Xe3fuC5egjtt9o9dX8Ek+opACcCu3H
euSZyKGB9/HVcuwilQicfMM=
=bQo7
-----END PGP SIGNATURE-----

_______________________________________________
freebsd-stable@xxxxxxxxxxx mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "freebsd-stable-unsubscribe@xxxxxxxxxxx"

Relevant Pages

  • Re: SMS requests
    ... There is also an operator command to display the subsystem interface and the subsystems for which that subfunction is available but even that command doesn't return anything for SMS. ... Subject: SMS requests> To: IBM-MAIN@xxxxxxxxxxx>> Take a look in ...
    (bit.listserv.ibm-main)
  • Re: SMS requests
    ... Does anyone know if SUSBSYSTEM requests to SMS are documented ... send email to listserv@xxxxxxxxxxx with the message: GET IBM-MAIN INFO ... Search the archives at http://bama.ua.edu/archives/ibm-main.html ...
    (bit.listserv.ibm-main)
  • Re: SMS requests
    ... Actually, if you didn't want to get into programming too much, a look in ... Does anyone know if SUSBSYSTEM requests to SMS are documented ... Search the archives at http://bama.ua.edu/archives/ibm-main.html ...
    (bit.listserv.ibm-main)
  • Re: XPsp2 - firewall enable/disable based on net
    ... That's why you configure exceptions for the local IP address range. ... requests from other addresses will be denied. ... > Ports must be available for sms and other software while on corporate ...
    (microsoft.public.windowsxp.security_admin)
  • Re: deadlock in "zoneli" state on 6.2-PRERELEASE
    ... requests for sfbufs delayed ... requests for I/O initiated by sendfile ... 173 calls to protocol drain routines ... 130465/480 mbuf+clusters out of packet secondary zone in use ...
    (freebsd-stable)