Date: Mon, 14 Nov 2011 07:30:41 -0600 (CST) From: Dan The Man <dan@sunsaturn.com> To: freebsd-current@freebsd.org Subject: Re: samba+zfs Message-ID: <alpine.BSF.2.00.1111140714120.1814@sunsaturn.com> In-Reply-To: <alpine.BSF.2.00.1111140253450.1814@sunsaturn.com> References: <alpine.BSF.2.00.1110272039500.50739@sunsaturn.com> <CAGH67wRZZx0hG9ug2k-5ohCOPJ9sZOU9iFVKg7hv9WM=R761GA@mail.gmail.com> <alpine.BSF.2.00.1111080259270.89703@sunsaturn.com> <alpine.BSF.2.00.1111080328010.89703@sunsaturn.com> <CALM%2B6aJkF=CFq8LA3FrSMYo8La-8txK4h2p4yZtdHshskBU6Vw@mail.gmail.com> <alpine.BSF.2.00.1111082015260.93923@sunsaturn.com> <CALM%2B6aJiM%2BNfikax9vNiYzBJqo3B8WLEXiZgrjUUQa9ngCQaKg@mail.gmail.com> <B4FEAF5B-52AC-40E5-90A3-7BD060BB7A73@gsoft.com.au> <F8AEDB62-4C76-4D95-8CBA-6C58B54C1965@gsoft.com.au> <CAGH67wRJkN%2BsDhxxMVSZx3RXQJm5xyyfW9iwiY1FrkFxLu%2BTWQ@mail.gmail.com> <82C85C01-62C4-4E75-B3F2-59D703CA5D78@gsoft.com.au> <CALM%2B6aK3PgdPNZJEHCdday84tH_7P9Ug=_yk=PfxcFOV6ejEzA@mail.gmail.com> <alpine.BSF.2.00.1111120444440.65294@sunsaturn.com> <alpine.BSF.2.00.1111140253450.1814@sunsaturn.com>
next in thread | previous in thread | raw e-mail | index | archive | help
Thankyou for suggestion Peter , didn't solve it, and no its not the disks
, I have been monitoring gstat and its doing what it should, NFS works
just fine.
Here is typical NFS session from tcpdump
07:13:42.192671 IP asterisk.nfsd > desktop.kink: Flags [.], ack 19048093,
win 29124, length 0
07:13:42.192673 IP desktop.kink > asterisk.nfsd: Flags [.], seq
19048093:19049553, ack 16176768, win 16178, length 1460
07:13:42.192679 IP asterisk.nfsd > desktop.kink: Flags [.], ack 19049553,
win 29124, length 0
07:13:42.192680 IP desktop.kink > asterisk.nfsd: Flags [.], seq
19049553:19051013, ack 16176768, win 16178, length 1460
07:13:42.192686 IP asterisk.nfsd > desktop.kink: Flags [.], ack 19051013,
win 29124, length 0
07:13:42.192765 IP desktop.kink > asterisk.nfsd: Flags [.], seq
19051013:19052473, ack 16176768, win 16178, length 1460
07:13:42.192771 IP asterisk.nfsd > desktop.kink: Flags [.], ack 19052473,
win 29124, length 0
07:13:42.192772 IP desktop.kink > asterisk.nfsd: Flags [.], seq
19052473:19053933, ack 16176768, win 16178, length 1460
07:13:42.192778 IP asterisk.nfsd > desktop.kink: Flags [.], ack 19053933,
win 29124, length 0
07:13:42.192780 IP desktop.kink > asterisk.nfsd: Flags [.], seq
19053933:19055393, ack 16176768, win 16178, length 1460
07:13:42.192786 IP asterisk.nfsd > desktop.kink: Flags [.], ack 19055393,
win 29124, length 0
07:13:42.192787 IP desktop.kink > asterisk.nfsd: Flags [.], seq
19055393:19056853, ack 16176768, win 16178, length 1460
07:13:42.192793 IP asterisk.nfsd > desktop.kink: Flags [.], ack 19056853,
win 29124, length 0
07:13:42.192795 IP desktop.kink > asterisk.nfsd: Flags [.], seq
19056853:19058313, ack 16176768, win 16178, length 1460
Its always sitting in rpcsvc around 2% cpu doing what it should.
Samba on other hand what I find interesting is I tried to see what truss
would show on smbd while writing today and found the following:
#################################################################################
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.939217, 10]"...,67) = 67 (0x43)
geteuid() = 0 (0x0)
write(36," Running timed event "smbd_idle"...,60) = 60 (0x3c)
gettimeofday({1321277167.939372 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.939372, 10]"...,77) = 77 (0x4d)
geteuid() = 0 (0x0)
write(36," smbd_idle_event_handler: idle_"...,57) = 57 (0x39)
gettimeofday({1321277167.939521 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.939521, 10]"...,77) = 77 (0x4d)
geteuid() = 0 (0x0)
write(36," smbd_idle_event_handler: idle_"...,62) = 62 (0x3e)
gettimeofday({1321277167.939671 },0x0) = 0 (0x0)
gettimeofday({1321277167.939700 },0x0) = 0 (0x0)
gettimeofday({1321277167.939728 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.939728, 10]"...,67) = 67 (0x43)
geteuid() = 0 (0x0)
write(36," Running timed event "smbd_idle"...,60) = 60 (0x3c)
gettimeofday({1321277167.939877 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.939877, 10]"...,77) = 77 (0x4d)
geteuid() = 0 (0x0)
write(36," smbd_idle_event_handler: idle_"...,61) = 61 (0x3d)
gettimeofday({1321277167.940031 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.940031, 5]"...,70) = 70 (0x46)
geteuid() = 0 (0x0)
write(36," housekeeping\n",15) = 15 (0xf)
gettimeofday({1321277167.940177 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.940177, 4]"...,65) = 65 (0x41)
geteuid() = 0 (0x0)
write(36," setting sec ctx (0, 0) - sec_c"...,49) = 49 (0x31)
gettimeofday({1321277167.940327 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.940327, 5]"...,94) = 94 (0x5e)
geteuid() = 0 (0x0)
write(36," Security token: (NULL)\n",25) = 25 (0x19)
gettimeofday({1321277167.940475 },0x0) = 0 (0x0)
geteuid() = 0 (0x0)
write(36,"[2011/11/14 07:26:07.940475, 5]"...,78) = 78 (0x4e)
geteuid() = 0 (0x0)
write(36," UNIX token of user 0\n",23) = 23 (0x17)
geteuid() = 0 (0x0)
write(36," Primary group is 0 and contain"...,57) = 57 (0x39)
geteuid() = 0 (0x0)
getegid() = 0 (0x0)
__sysctl(0x7fffffffd170,0x2,0x7fffffffd18c,0x7fffffffd180,0x0,0x0) = 0
(0x0)
It actually seems to be running some timed event smbd_idle literally
holding up process for many seconds all the time....
Dan,
--
Dan The Man
CTO/ Senior System Administrator
Websites, Domains and Everything else
http://www.SunSaturn.com
Email: Dan@SunSaturn.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?alpine.BSF.2.00.1111140714120.1814>