Mailing List
Home
Forum Home
Linux - General Red Hat Linux discussion list
Installation - Getting started with Red Hat Linux
Enterprise Linux 3 - Discussion of Red Hat Enterprise Linux 3 (Taroon)
Red Hat Linux 9 - Discussion of Red Hat Linux 9 (Shrike)
Red Hat Linux 7.2 - Discussion of Red Hat Linux 7.2 (Enigma)
Red Hat Linux 7.3 - Discussion of Red Hat Linux 7.3 (Valhalla)
Apache Web Server
Oracle database, Microsoft SQL server ...
Subjects
application/x mplayer2 plugin
RPM error: db4 error(16) from dbenv >remove: Device or resource
   busy
Command stream end of file while reading
X Windows problem (xauth)
Upgrading openoffice 1 1 rpm
FTP: connection refused
FTP: connection refused
mount: /dev/cdrom: is not a valid block device
Dell Precision 650, RedHat 9, no sound
how to trace the cause resulting in the crash of bind server
Virus on the list
UNINSTALL RPM MYSQL
usb pen drives: mounting as a user
broadcom network interface
make mrproper
Couldn 't open PID file /var/run/named/named pid Permission denied
sendmail configuration on redhat
kernel 2 6 and /dev/sound/mixer not found
Promise 378 controller
Problem using up2date
mrtg step by step howto/configuration for a newbie?
Compiling and Installing Kernel 2 6
Can 't locate module ppp0, can 't locate module ppp compress 21
Lotus Notes under Wine
HOW I CAN MAKE BOOTABLE FLOPPY DISKET
/etc/security/limits conf question
Intel E/1000 driver
rpm database corrupt
Command stream end of file while reading
qla2300 modules
 
System hang problem.

System hang problem.

2006-10-03       - By Paul Krizak

 Back
Reply:     1     2     3     4     5     6     7     8     9     10     >>  

We've had similar issues with the OOM killer in RHEL3.  We've found it
to be pretty much worthless on our large memory systems.  We've kept it
enabled on our <= 8GB servers because it seems to work reasonably well
there, but in many cases, the OOM killer will kill important things like
the portmapper or ypbind instead of the giant 12G process that was
hosing the system.  I'm genuinely interested in understanding how the
OOM killer algorithm selects processes to kill...

We're running RHEL3U8 btw...

Paul Krizak                         5900 E. Ben White Blvd. MS 625
Advanced Micro Devices              Austin, TX  78741
Linux/Unix Systems Engineering      Phone: (512) 602-8775
Silicon Design Division


Manish Neema wrote:
> We see this problem frequently on RHEL3.0 U5 and U7. System would
> completely hang upon memory shortage. The only option left is
> power-cycle (or 'sysrq + b'). System hang occurs with any of the below 3
> overcommit settings:
>
>    - default (heuristic) overcommit (overcommit_memory=0)
>    - no overcommit handling by kernel (overcommit_memory=1)
>    - restrictive overcommit with ratio=100% (overcommit_memory=2;
> overcommit_ratio=100)
>
> RHEL3.0 U3 would generate an OOM kill "each and every time" it sensed
> system hang but due to other bugs, we had to move away from it. RedHat
> support calls the timely (at least for us) invocation of OOM in U3 a
> buggy implementation and the delayed OOM kill in U5 and U7 the right
> implementation (which we rarely get to see resulting in at least 5
> systems hanging daily!)
>
> Changing overcommit to 2 (and ratio to any where from 1 to 99) would
> result in certain OS processes (automount daemon for e.g.) getting
> killed when all the allowed memory is committed. What is the point in
> reserving some memory if a random root process would get killed leaving
> the system in a totally unknown state?
>
> Any suggestions on how we can prevent system-hang + not have automount
> (and any other root process) die?
>
> TIA,
> -Manish Neema
>
> P.S. Sorry, we cannot move away from RHEL3.0 U7 for a while.
>
> --
> Taroon-list mailing list
> Taroon-list@(protected)
> https://www.redhat.com/mailman/listinfo/taroon-list
>
>


--
Taroon-list mailing list
Taroon-list@(protected)
https://www.redhat.com/mailman/listinfo/taroon-list