Date: Thu, 30 Mar 2006 16:11:58 -0700 (MST) From: Matt Ruzicka <matt@frii.com> To: Jorge Evangelista <netsecuredata@gmail.com> Cc: freebsd-isp@freebsd.org Subject: Re: Problem sometimes Freebsd crash Message-ID: <Pine.BSF.4.64.0603301603440.36186@elara.frii.com> In-Reply-To: <de85c96f0603301327s151caf19ra7c7195965d6e48f@mail.gmail.com> References: <de85c96f0603301327s151caf19ra7c7195965d6e48f@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
I don't have any experience with Bandwidth Manager so I'm not really sure what it should be doing in this case. I can say that we had something similar happen to us a while back on our web servers with the same symptoms. I wasn't really part of that project at the time, but I know we have the entry kern.ipc.nmbclusters="16384" in our /boot/loader.conf to specifically up the mbuffs. I don't remember if we also needed to add anything to our kernel specifically as well though. I'd check out the tuning man page as the error indicates to see what can be done to increase the mbufs. It is likely that bwmgrd isn't able to affect the mbuf maximums because it is kernel or boot time setting and can't be changed once the box is running. Good luck. Matthew Ruzicka - Systems Administrator Front Range Internet, Inc. matt@frii.net - (970) 212-0728 Got SPAM? Take back your email with MailArmory. http://www.MailArmory.com On Thu, 30 Mar 2006, Jorge Evangelista wrote: > Hi friends, > > My name is Jorge, i am from Peru, excuse me for my english, I have a > server with FreeBSD 4.11-RELEASE #2 and Bandwitdh Manager (bwmgrd), > but I have many problems with it, I have rise up mbuf clusters in my > server to 16384 (It I have made in the file /boot/loader.conf), before > It was configured to 12000. Now I do not have logs about > > Mar 3 20:42:57 trafico /kernel: All mbuf clusters exhausted, please > see tuning(7). > Mar 3 20:46:49 trafico /kernel: All mbuf clusters exhausted, please > see tuning(7). > Mar 3 20:46:52 trafico /kernel: All mbuf clusters exhausted, please > see tuning(7). > Mar 9 20:31:24 trafico /kernel: All mbuf clusters exhausted, please > see tuning(7). > Mar 9 20:31:27 trafico /kernel: All mbuf clusters exhausted, please > see tuning(7). > > However, sometimes my server still hang, crash. I have to reboot the > server for that I work again. If I have enough memory, why bwmgrd no > use it, I do not why it said 59 requests for memory denied > > > > > There are some logs > > #netstat -m > > 1881/9050/16384 mbuf clusters in use (current/peak/max) > 20364 Kbytes allocated to network (41% of mb_map in use) > 59 requests for memory denied > 0 requests for memory delayed > 0 calls to protocol drain routines > > > This is report of my server memory > > # muse -m > Active: 34.305 MB > Inactive: 171.328 MB > Wired: 133.832 MB > Reserved: 1.949 MB > Cache: 0.000 MB > Kernel: 0.133 MB > Interrupt: 0.008 MB > Buffer: 137.203 MB > > Total: 1252.453 MB > Free: 912.988 MB > > > ET/BWMGR Driver v3.25b > > Thanks, for your help. > > -- > "The network is the computer" > _______________________________________________ > freebsd-isp@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-isp > To unsubscribe, send any mail to "freebsd-isp-unsubscribe@freebsd.org" >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.64.0603301603440.36186>