Bug in GEOM or in gstat?
Hi there, when running gstat I'm seeing things like this: dT: 0.509 flag_I 50us sizeof 240 i -1 L(q) ops/sr/s kBps ms/rw/s kBps ms/w %busy Name 1189149 21136.2 39785 20.6 87.8| da0 1226218 8891 14.2 8785 24.6 94.3| da1 0104 49 2144 10.7 55 7037 34.0 58.3| da2 1189149 21136.2 39785 20.9 88.4| da0s1 1226218 8891 14.2 8785 24.7 94.4| da1s1 0104 49 2144 10.8 55 7037 34.1 58.4| da2s1 0 0 0 00.0 0 00.00.0| da0s1a 0 2 2 8 10.9 0 00.02.1| da0s1b 0 0 0 00.0 0 00.00.0| da0s1c 0 0 0 00.0 0 00.00.0| da0s1d 0 0 0 00.0 0 00.00.0| da0s1e 0 0 0 00.0 0 00.00.0| da0s1f 4294967295187147 21056.2 39785 21.2 99.0| da0s1g 0 0 0 00.0 0 00.00.0| da1s1c 0 0 0 00.0 0 00.00.0| da1s1d 4294967295226218 8891 14.3 8785 24.8 89.7| da1s1e 0 0 0 00.0 0 00.00.0| da2s1c 0 0 0 00.0 0 00.00.0| da2s1d 0104 49 2144 10.8 55 7037 34.3 58.5| da2s1e Notice the high numbers in the L(q) row, this seems like an underflow somewhere. The numbers don't stay like that, they are fluctuating. regards, le -- Lukas Ertl eMail: [EMAIL PROTECTED] UNIX Systemadministrator Tel.: (+43 1) 4277-14073 Vienna University Computer Center Fax.: (+43 1) 4277-9140 University of Vienna http://mailbox.univie.ac.at/~le/ ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Bug in GEOM or in gstat?
Hi Lucas, Which versions ? 5.0, 5.1 or -current ? Does the large numbers persist when the system is idle, or do they fall back to zero ? Poul-Henning In message [EMAIL PROTECTED], Lukas Ertl writes: Hi there, when running gstat I'm seeing things like this: dT: 0.509 flag_I 50us sizeof 240 i -1 L(q) ops/sr/s kBps ms/rw/s kBps ms/w %busy Name 1189149 21136.2 39785 20.6 87.8| da0 1226218 8891 14.2 8785 24.6 94.3| da1 0104 49 2144 10.7 55 7037 34.0 58.3| da2 1189149 21136.2 39785 20.9 88.4| da0s1 1226218 8891 14.2 8785 24.7 94.4| da1s1 0104 49 2144 10.8 55 7037 34.1 58.4| da2s1 0 0 0 00.0 0 00.00.0| da0s1a 0 2 2 8 10.9 0 00.02.1| da0s1b 0 0 0 00.0 0 00.00.0| da0s1c 0 0 0 00.0 0 00.00.0| da0s1d 0 0 0 00.0 0 00.00.0| da0s1e 0 0 0 00.0 0 00.00.0| da0s1f 4294967295187147 21056.2 39785 21.2 99.0| da0s1g 0 0 0 00.0 0 00.00.0| da1s1c 0 0 0 00.0 0 00.00.0| da1s1d 4294967295226218 8891 14.3 8785 24.8 89.7| da1s1e 0 0 0 00.0 0 00.00.0| da2s1c 0 0 0 00.0 0 00.00.0| da2s1d 0104 49 2144 10.8 55 7037 34.3 58.5| da2s1e Notice the high numbers in the L(q) row, this seems like an underflow somewhere. The numbers don't stay like that, they are fluctuating. regards, le -- Lukas Ertl eMail: [EMAIL PROTECTED] UNIX Systemadministrator Tel.: (+43 1) 4277-14073 Vienna University Computer Center Fax.: (+43 1) 4277-9140 University of Vienna http://mailbox.univie.ac.at/~le/ -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 [EMAIL PROTECTED] | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Bug in GEOM or in gstat?
On Mon, 4 Aug 2003, Poul-Henning Kamp wrote: Hi Lucas, Which versions ? 5.0, 5.1 or -current ? CURRENT from this morning CEST. Does the large numbers persist when the system is idle, or do they fall back to zero ? This is a snapshot from an idle system: dT: 0.510 flag_I 50us sizeof 240 i -1 L(q) ops/sr/s kBps ms/rw/s kBps ms/w %busy Name 0 4 0 00.0 4 63 10.52.6| da0 0 20 0 00.0 20314 25.1 10.0| da1 0 2 0 00.0 2 318.51.7| da2 0 4 0 00.0 4 63 10.62.6| da0s1 0 20 0 00.0 20314 25.2 10.0| da1s1 0 2 0 00.0 2 318.51.7| da2s1 0 0 0 00.0 0 00.00.0| da0s1a 0 0 0 00.0 0 00.00.0| da0s1b 0 0 0 00.0 0 00.00.0| da0s1c 0 0 0 00.0 0 00.00.0| da0s1d 0 0 0 00.0 0 00.00.0| da0s1e 0 0 0 00.0 0 00.00.0| da0s1f 4294967293 4 0 00.0 4 63 10.6 561.0| da0s1g 0 0 0 00.0 0 00.00.0| da1s1c 0 0 0 00.0 0 00.00.0| da1s1d 4294967294 20 0 00.0 20314 25.2 10.0| da1s1e 0 0 0 00.0 0 00.00.0| da2s1c 0 0 0 00.0 0 00.00.0| da2s1d 0 2 0 00.0 2 318.51.7| da2s1e 561% busy is nice, too :-) regards, le -- Lukas Ertl eMail: [EMAIL PROTECTED] UNIX Systemadministrator Tel.: (+43 1) 4277-14073 Vienna University Computer Center Fax.: (+43 1) 4277-9140 University of Vienna http://mailbox.univie.ac.at/~le/ ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: Bug in GEOM or in gstat?
On Mon, 4 Aug 2003, Lukas Ertl wrote: This is a snapshot from an idle system: dT: 0.510 flag_I 50us sizeof 240 i -1 0 0 0 00.0 0 00.00.0| da0s1f 4294967293 4 0 00.0 4 63 10.6 561.0| da0s1g 0 0 0 00.0 0 00.00.0| da1s1c 0 0 0 00.0 0 00.00.0| da1s1d 4294967294 20 0 00.0 20314 25.2 10.0| da1s1e To clarify that: on the idle system the high numbers for L(q) don't fall back to 0 again. regards, le -- Lukas Ertl eMail: [EMAIL PROTECTED] UNIX Systemadministrator Tel.: (+43 1) 4277-14073 Vienna University Computer Center Fax.: (+43 1) 4277-9140 University of Vienna http://mailbox.univie.ac.at/~le/ ___ [EMAIL PROTECTED] mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-current To unsubscribe, send any mail to [EMAIL PROTECTED]
