Quoting Julian Wissmann <julianwissm...@gmail.com> (from Wed, 8 Feb
2012 18:33:53 +0100):
1086 tor RET read 1568/0x620
1086 tor CALL clock_gettime(0xd,0x7fffffffd910)
1086 tor RET clock_gettime 0
1086 tor CALL
kevent(0x3,0x3e18000,0x2,0x3dbe000,0x400,0x7fffffffd920)
1086 tor GIO fd 3 wrote 64 bytes
1086 tor RET kevent 3
1086 tor CALL clock_gettime(0x4,0x7fffffffd940)
1086 tor RET clock_gettime 0
1086 tor CALL gettimeofday(0x7fffffffd930,0)
1086 tor RET gettimeofday 0
1086 tor CALL recvfrom(0xbc2,0x4822020,0x3e40,0,0,0)
1086 tor GIO fd 3010 read 4096 bytes
As I understand kevent to be part of queue I go with yes here. What
I also take from it is a huge number of clock_gettime() and
gettimeofday() calls.
And there you have probably the cause of the slowdown. The clock
subsystem in FreeBSD is working at a higher prcession than what you
get in FreeBSD. If possible, try to trim down the number of calls, or
use a less precise (and faster) clocksource, e.g. one of the _FAST
ones (see http://www.freebsd.org/cgi/man.cgi?clock_gettime).
Bye,
Alexander.
--
Corruption is not the No. 1 priority of the Police Commissioner.
His job is to enforce the law and fight crime.
-- P.B.A. President E. J. Kiernan
http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID = B0063FE7
http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID = 72077137
_______________________________________________
freebsd-performance@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-performance
To unsubscribe, send any mail to "freebsd-performance-unsubscr...@freebsd.org"
