Date: Sun, 15 Feb 2004 17:13:39 -0600 (CST) From: matt <matt@grogged.dyndns.org> To: sparc64@freebsd.org Subject: 64 bit time_t oddness Message-ID: <20040215165913.M30161@grogged.dyndns.org> In-Reply-To: <p0602040ebc54c885236b@[128.113.24.47]> References: <p06020407bc533f0ae9d2@[128.113.24.47]> <20040215060047.GA62840@dhcp01.pn.xcllnt.net> <p0602040ebc54c885236b@[128.113.24.47]>
next in thread | previous in thread | raw e-mail | index | archive | help
Finally got around to testing this out over the weekend. The 64 bit
time_t updating instructions/script seem to work pretty well on at least
one of the sparcs here (Tatung Axi 440Mhz/1gb/36gb local scsi disk). I
have a couple dual Ultra 2's (296Mhz) with an nfs mounted root/usr that I
will try if the thing ever finishes compiling (damn shame MP on the U2's
is broken, had to pull out one of the cpu's to boot through a kernel).
Anyhow, here is the strangeness. After compiling/installing the 64 bit
time_t world/kernel, I'm getting some serious lag on this machine. When
logged in via ssh, the shell freezes every few seconds for a brief period
of time. Then I get this with top -S:
last pid: 81822; load averages: 1.18, 1.06, 0.98 up 0+01:18:40
23:03:20
46 processes: 2 running, 28 sleeping, 16 waiting
CPU states: 8.9% user, 0.0% nice, 72.3% system, 0.0% interrupt, 18.8%
idle
Mem: 11M Active, 5368K Inact, 19M Wired, 32K Cache, 8848K Buf, 954M Free
Swap: 2022M Total, 2022M Free
PID USERNAME PRI NICE SIZE RES STATE TIME WCPU CPU COMMAND
11 root -16 0 0K 40K RUN 31:42 38.96% 38.96% idle:
cpu0
8 root 171 52 0K 40K pgzero 1:12 3.96% 3.96% pagezero
473 root 130 0 3624K 1952K select 0:47 0.00% 0.00% dhclient
13 root -16 -135 0K 40K WAIT 0:19 0.00% 0.00% swi8:
clock
239 root 76 0 3688K 1088K select 0:10 0.00% 0.00% syslogd
688 matt 76 0 29720K 3672K select 0:04 0.00% 0.00% sshd
27 root -68 -187 0K 40K WAIT 0:02 0.00% 0.00%
intr2017: hme
4 root -8 0 0K 40K - 0:02 0.00% 0.00% g_down
377 root 81 0 18744K 2800K select 0:01 0.00% 0.00% sshd
<snip)
At any given time, I only seem to have ~40% (or less) cpu available for
anything. The clean make buildworld/buildkernel with 32 bit time_t
didn't have this problem, the sources are identicle (no cvsup's between
builds). The sources were updated before I started playing with
anything, as of yesterday (the 14th). I let the machien run for a few
hours like this, it's still grinding away on... something.
-m
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20040215165913.M30161>