* [Adeos-main] ipipe-2.6.34-x86-2.6-04: The magical RAM increaser
@ 2010-05-31 17:05 Jan Kiszka
2010-05-31 17:59 ` Philippe Gerum
0 siblings, 1 reply; 3+ messages in thread
From: Jan Kiszka @ 2010-05-31 17:05 UTC (permalink / raw)
To: Philippe Gerum; +Cc: adeos-main
Hi Philippe,
something is fishy in I-pipe for 2.6.34 (both w/ and w/o Xenomai,
goes away once I-pipe is off):
top - 18:55:26 up 3 min, 2 users, load average: 2.09, 1.42, 0.58
Tasks: 60 total, 1 running, 59 sleeping, 0 stopped, 0 zombie
Cpu(s): 0.0%us, 24.7%sy, 0.0%ni, 75.3%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 1012496k total, 121264k used, 891232k free, 4676k buffers
Swap: 1156644k total, 0k used, 1156644k free, 80748k cached
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
5636 root 20 0 51776 3.7t 3.7t S 0.0 392333.0 0:00.01 sshd
4195 haldaemo 20 0 34220 1.8t 1.8t S 0.0 188901.4 0:02.10 hald
5327 root 20 0 19036 1.5t 1.5t S 0.0 159839.4 0:00.15 syslog-ng
5495 root 20 0 164m 1.4t 1.4t S 0.0 145308.6 0:00.23 nscd
5563 root 20 0 16240 1.4t 1.4t S 0.0 145308.6 0:00.01 smartd
5523 root 20 0 10204 982g 982g S 0.0 101716.0 0:00.01 avahi-dnsconfd
5330 root 20 0 4012 701g 701g S 0.0 72654.3 0:00.04 klogd
4154 root 20 0 3872 561g 561g S 0.0 58123.4 0:00.04 acpid
5991 root 20 0 13264 2356 1596 S 0.0 0.2 0:00.34 bash
I swear this machine does *not* yet have Tera bytes of RAM (just 1G).
Looks like /proc/<pid>/stat is broken, likely even something deeper.
Philippe, did you ran into suspicious conflicts in the mm subsystem
while rebasing over this kernel? Any spontaneous idea?
Jan
--
Siemens AG, Corporate Technology, CT T DE IT 1
Corporate Competence Center Embedded Linux
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [Adeos-main] ipipe-2.6.34-x86-2.6-04: The magical RAM increaser
2010-05-31 17:05 [Adeos-main] ipipe-2.6.34-x86-2.6-04: The magical RAM increaser Jan Kiszka
@ 2010-05-31 17:59 ` Philippe Gerum
2010-05-31 18:03 ` Philippe Gerum
0 siblings, 1 reply; 3+ messages in thread
From: Philippe Gerum @ 2010-05-31 17:59 UTC (permalink / raw)
To: Jan Kiszka; +Cc: adeos-main
On Mon, 2010-05-31 at 19:05 +0200, Jan Kiszka wrote:
> Hi Philippe,
>
> something is fishy in I-pipe for 2.6.34 (both w/ and w/o Xenomai,
> goes away once I-pipe is off):
>
> top - 18:55:26 up 3 min, 2 users, load average: 2.09, 1.42, 0.58
> Tasks: 60 total, 1 running, 59 sleeping, 0 stopped, 0 zombie
> Cpu(s): 0.0%us, 24.7%sy, 0.0%ni, 75.3%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
> Mem: 1012496k total, 121264k used, 891232k free, 4676k buffers
> Swap: 1156644k total, 0k used, 1156644k free, 80748k cached
>
> PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> 5636 root 20 0 51776 3.7t 3.7t S 0.0 392333.0 0:00.01 sshd
> 4195 haldaemo 20 0 34220 1.8t 1.8t S 0.0 188901.4 0:02.10 hald
> 5327 root 20 0 19036 1.5t 1.5t S 0.0 159839.4 0:00.15 syslog-ng
> 5495 root 20 0 164m 1.4t 1.4t S 0.0 145308.6 0:00.23 nscd
> 5563 root 20 0 16240 1.4t 1.4t S 0.0 145308.6 0:00.01 smartd
> 5523 root 20 0 10204 982g 982g S 0.0 101716.0 0:00.01 avahi-dnsconfd
> 5330 root 20 0 4012 701g 701g S 0.0 72654.3 0:00.04 klogd
> 4154 root 20 0 3872 561g 561g S 0.0 58123.4 0:00.04 acpid
> 5991 root 20 0 13264 2356 1596 S 0.0 0.2 0:00.34 bash
>
> I swear this machine does *not* yet have Tera bytes of RAM (just 1G).
>
> Looks like /proc/<pid>/stat is broken, likely even something deeper.
> Philippe, did you ran into suspicious conflicts in the mm subsystem
> while rebasing over this kernel? Any spontaneous idea?
Bad hunks in mm/memory.c.
>
> Jan
>
--
Philippe.
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [Adeos-main] ipipe-2.6.34-x86-2.6-04: The magical RAM increaser
2010-05-31 17:59 ` Philippe Gerum
@ 2010-05-31 18:03 ` Philippe Gerum
0 siblings, 0 replies; 3+ messages in thread
From: Philippe Gerum @ 2010-05-31 18:03 UTC (permalink / raw)
To: Jan Kiszka; +Cc: adeos-main
On Mon, 2010-05-31 at 19:59 +0200, Philippe Gerum wrote:
> On Mon, 2010-05-31 at 19:05 +0200, Jan Kiszka wrote:
> > Hi Philippe,
> >
> > something is fishy in I-pipe for 2.6.34 (both w/ and w/o Xenomai,
> > goes away once I-pipe is off):
> >
> > top - 18:55:26 up 3 min, 2 users, load average: 2.09, 1.42, 0.58
> > Tasks: 60 total, 1 running, 59 sleeping, 0 stopped, 0 zombie
> > Cpu(s): 0.0%us, 24.7%sy, 0.0%ni, 75.3%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st
> > Mem: 1012496k total, 121264k used, 891232k free, 4676k buffers
> > Swap: 1156644k total, 0k used, 1156644k free, 80748k cached
> >
> > PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
> > 5636 root 20 0 51776 3.7t 3.7t S 0.0 392333.0 0:00.01 sshd
> > 4195 haldaemo 20 0 34220 1.8t 1.8t S 0.0 188901.4 0:02.10 hald
> > 5327 root 20 0 19036 1.5t 1.5t S 0.0 159839.4 0:00.15 syslog-ng
> > 5495 root 20 0 164m 1.4t 1.4t S 0.0 145308.6 0:00.23 nscd
> > 5563 root 20 0 16240 1.4t 1.4t S 0.0 145308.6 0:00.01 smartd
> > 5523 root 20 0 10204 982g 982g S 0.0 101716.0 0:00.01 avahi-dnsconfd
> > 5330 root 20 0 4012 701g 701g S 0.0 72654.3 0:00.04 klogd
> > 4154 root 20 0 3872 561g 561g S 0.0 58123.4 0:00.04 acpid
> > 5991 root 20 0 13264 2356 1596 S 0.0 0.2 0:00.34 bash
> >
> > I swear this machine does *not* yet have Tera bytes of RAM (just 1G).
> >
> > Looks like /proc/<pid>/stat is broken, likely even something deeper.
> > Philippe, did you ran into suspicious conflicts in the mm subsystem
> > while rebasing over this kernel? Any spontaneous idea?
>
> Bad hunks in mm/memory.c.
This might even date back to 2.6.33, with changes in the vm accounting
IIRC.
>
> >
> > Jan
> >
>
>
--
Philippe.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2010-05-31 18:03 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-05-31 17:05 [Adeos-main] ipipe-2.6.34-x86-2.6-04: The magical RAM increaser Jan Kiszka
2010-05-31 17:59 ` Philippe Gerum
2010-05-31 18:03 ` Philippe Gerum
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.