Re: cron stops silently
On 5/27/05, Dick Davies [EMAIL PROTECTED] wrote: * Kirk Strauser [EMAIL PROTECTED] [0538 15:38]: On Friday 27 May 2005 08:05, Dean Strik wrote: I just filed PR 81555 about this. For me, it appears that cron(8) exits after a SIGPIPE when an LDAP-user does a crontab -e. Are you also using LDAP here? See also the PR (hasn't appeared on the website when I type this btw). aol Me too /aol Me three - 5.4 and nss_ldap. -- 'You may need to metaphorically make a deal with the devil. By 'devil' I mean robot devil and by 'metaphorically' I mean get your coat.' -- Bender Rasputin :: Jack of All Trades - Master of Nuns Just in case anyone missed it,Dean Strik has a patch for this at the pr page: http://www.freebsd.org/cgi/query-pr.cgi?pr=81555 applied cleanly for me. ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
cron stops silently
Hi, Since updating our server to 5.4-STABLE, I've noticed a very strange problem with cron. Sometimes it just decides to stop, for no apparent reason. It stops at different times, it doesn't seem to be affected by any particular cronjob. There are no messages about this in any logfile, it just stops running and I have to start it manually. Obviously this is a major PITA. Can anyone help me to debug this problem further? I really don't know where to look. Searches of all freebsd mailing lists have turned up with nothing. Regards, Philip Brennan ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
cron stops silently
From: Phil Brennan [EMAIL PROTECTED] Date: May 27, 2005 1:30 PM Subject: Re: cron stops silently To: Dean Strik [EMAIL PROTECTED] On 5/27/05, Dean Strik [EMAIL PROTECTED] wrote: Phil Brennan wrote: Since updating our server to 5.4-STABLE, I've noticed a very strange problem with cron. Sometimes it just decides to stop, for no apparent reason. It stops at different times, it doesn't seem to be affected by any particular cronjob. There are no messages about this in any logfile, it just stops running and I have to start it manually. Obviously this is a major PITA. Can anyone help me to debug this problem further? I really don't know where to look. Searches of all freebsd mailing lists have turned up with nothing. I just filed PR 81555 about this. For me, it appears that cron(8) exits after a SIGPIPE when an LDAP-user does a crontab -e. Are you also using LDAP here? See also the PR (hasn't appeared on the website when I type this btw). http://www.freebsd.org/cgi/query-pr.cgi?pr=81555 -- Dean C. Strik Eindhoven University of Technology [EMAIL PROTECTED] | [EMAIL PROTECTED] | http://www.ipnet6.org/ This isn't right. This isn't even wrong. -- Wolfgang Pauli aha, I had a faint suspicion that was it. Yes, I'm using ldap, and I've just managed to reproduce the problem. I'm wondering if this has anything to do with nss_ldap, I haven't rebuilt it since moving from 5.2.1-Release to 5-STABLE. Did you do a fresh install or an upgrade? Regards, Philip ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
updating from 5.2.1 to RELENG_5
As per subject, I need to do this urgently, but with minimum downtime. Will it be ok just to cvsup, rebuild kernel and world, mergemaster, (etc) like any normal update? Or do I have to do a reinstall? Any help appreciated. Regards, Philip Brennan ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: updating from 5.2.1 to RELENG_5
On Apr 1, 2005 12:49 PM, Joan Picanyol i Puig [EMAIL PROTECTED] wrote: * Phil Brennan [EMAIL PROTECTED] [20050401 12:19]: Will it be ok just to cvsup, rebuild kernel and world, mergemaster, (etc) like any normal update? Or do I have to do a reinstall? Read UPDATING (all of it). Read UPDATING (all of it). Yes, I always read it. Did you notice the 20041001 entry? You should be able to use libmap.conf to work around it until you recompile all your ports. Yes, it referrs to compat4x libraries. Not an issue for me, since I'm upgrading from 5.2.1 to RELENG_5. Regarding libmap, yes I have used it before. Basically, I'm looking for advice from people who have done this particular upgrade. Its an upgrade that should be straightforward. I was only wondering if there were any extra little gotchas that I should consider. Thanks for all the replies so far. Regards, Philip ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
performance under heavy load
Hi, I'd just like to give some credit to the freebsd developers for a job well done. A user on our system ( freebsd 5.2.1 smp ) managed with a runaway script to start up 500 intensive processes, raising the load average to about 200. We managed to remotely, over ssh get a somewhat responsive session and kill the offending processes. Yes, I know we shouldn't have let it happen in the first place, by putting in proper user limits and all that, but it was amazing that the machine still worked. We thought we'd have to reboot. Even with a load of nearly 200, the machine was still able to serve web pages :) Once the load came down past 60, the system feltl fully responsive again. On linux, we would have had to reboot in this situation. On a highly linux machine, you lose all control of the machine past a load of about 6 - 10. This just further vindicates my decision to use freebsd for this service. ( Its a shell server with about 100 active users, apache, nfs, mysql, ldap ). Just wanted to share a success story :) Regards, Philip Brennan ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: performance under heavy load
True, on that linux machine its more io load than anything else. But anyway, the problem was caused by fortune -l going into an infinite loop, and a script running this every 5 minutes. On Sat, 5 Mar 2005 11:58:08 -0500, Vlad [EMAIL PROTECTED] wrote: On a highly linux machine, you lose all control of the machine past a load of about 6 - 10. to be fair, I should note that as admin / user of few tens of servers running both systems, I can assure you that if your linux loses control with LA ~ 10, then something is seriously wrong with that server and it's not because of the linux (rather it's hardware or wrong kernel configuration). I had cases of LA climbing over 150 on linux machine - it was extremely slow but I could get it back to life w/o need for reboot. On Sat, 5 Mar 2005 16:28:09 +, Phil Brennan [EMAIL PROTECTED] wrote: Hi, I'd just like to give some credit to the freebsd developers for a job well done. A user on our system ( freebsd 5.2.1 smp ) managed with a runaway script to start up 500 intensive processes, raising the load average to about 200. We managed to remotely, over ssh get a somewhat responsive session and kill the offending processes. Yes, I know we shouldn't have let it happen in the first place, by putting in proper user limits and all that, but it was amazing that the machine still worked. We thought we'd have to reboot. Even with a load of nearly 200, the machine was still able to serve web pages :) Once the load came down past 60, the system feltl fully responsive again. On linux, we would have had to reboot in this situation. On a highly linux machine, you lose all control of the machine past a load of about 6 - 10. This just further vindicates my decision to use freebsd for this service. ( Its a shell server with about 100 active users, apache, nfs, mysql, ldap ). Just wanted to share a success story :) Regards, Philip Brennan ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED] -- Vlad ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]
Re: performance under heavy load
Thats impressive, do you know what spec that machine is? On Sat, 5 Mar 2005 19:04:43 +0100, Godwin Stewart [EMAIL PROTECTED] wrote: -BEGIN PGP SIGNED MESSAGE- Hash: SHA1 On Sat, 5 Mar 2005 11:58:08 -0500, Vlad [EMAIL PROTECTED] wrote: to be fair, I should note that as admin / user of few tens of servers running both systems, I can assure you that if your linux loses control with LA ~ 10, then something is seriously wrong with that server and it's not because of the linux (rather it's hardware or wrong kernel configuration). Agreed. If you look at the details on http://www.kernel.org, you'll see that the server is running Linux-2.6 and that the load average is constantly around 200. - -- G. Stewart - [EMAIL PROTECTED] I can remember when a good politician had to be 75 percent ability and 25 percent actor, but I can well see the day when the reverse could be true. -- Harry Truman -BEGIN PGP SIGNATURE- Version: GnuPG v1.4.0 (FreeBSD) iD8DBQFCKfS7K5oiGLo9AcYRArBJAJ4/Cubtab1IShcW2oSLnCJgM7FMVACgmiMs xt+xdT5ejnZJ5dxJd8SJ4BU= =Qlqk -END PGP SIGNATURE- ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED] ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to [EMAIL PROTECTED]