Hi! We have a silly Problem, we are using xen on 6 machines. Everything works beautiful, but one DomU sometimes takes 199 percent of CPU an hangs (says xm top). Only an xm destroy and recreate can "reaktivate" it again. Normally it takes only around 25-40 percent. Sometimes it happens 1 time per week but sometimes every day. There is no more load at hangtime than normal and xen writes nothing to the logfiles (DomU/Dom0). We already changed the Dom0 System (we have an identical machine) and the Kernel is the same as on the other Systems and was built without USB Support. Have anybody an idea where I have to search for a solution of this Problem? Or anybody who already solved it? :-) Thanks for Help! Felix Some system specs: Versions: xen-3.0.2-2 and xen-3.0-3.0.2+hg9697 (self compiled) Debian Sarge 64bit Intel(R) Pentium(R) D CPU 3.40GHz TYAN S5161 Mainboard 4GB RAM (tested) XFS Filesystem (only) 2.6.16.13-xen #2 SMP x86_64 GNU/Linux lspci 0000:00:00.0 Host bridge: Intel Corporation E7230 Memory Controller Hub (rev 81) 0000:00:01.0 PCI bridge: Intel Corporation E7230 PCI Express Root Port (rev 81) 0000:00:1c.0 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI Express Port 1 (rev 01) 0000:00:1c.4 PCI bridge: Intel Corporation 82801GR/GH/GHM (ICH7 Family) PCI Express Port 5 (rev 01) 0000:00:1d.0 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #1 (rev 01) 0000:00:1d.1 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #2 (rev 01) 0000:00:1d.2 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #3 (rev 01) 0000:00:1d.3 USB Controller: Intel Corporation 82801G (ICH7 Family) USB UHCI #4 (rev 01) 0000:00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1) 0000:00:1f.0 ISA bridge: Intel Corporation 82801GB/GR (ICH7 Family) LPC Interface Bridge (rev 01) 0000:00:1f.1 IDE interface: Intel Corporation 82801G (ICH7 Family) IDE Controller (rev 01) 0000:00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus Controller (rev 01) 0000:02:00.0 PCI bridge: Intel Corporation 6702PXH PCI Express-to-PCI Bridge A (rev 09) 0000:03:04.0 RAID bus controller: 3ware Inc 9550SX SATA-RAID 0000:04:00.0 Ethernet controller: Intel Corporation 82573V Gigabit Ethernet Controller (Copper) (rev 03) 0000:0a:02.0 Ethernet controller: Intel Corporation 82557/8/9 [Ethernet Pro 100] (rev 10) 0000:0a:05.0 VGA compatible controller: XGI - Xabre Graphics Inc Volari Z7 -- Turtle Entertainment GmbH Felix Jaussi, Senior Systems Administrator Technical Head of Events Siegburger Str. 189 50679 Koeln Germany fon. +49 221 880449-312 fax. +49 221 880449-399 http://www.turtle-entertainment.de/ _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
> -----Original Message----- > From: xen-users-bounces@lists.xensource.com > [mailto:xen-users-bounces@lists.xensource.com] On Behalf Of > Felix Jaussi > Sent: 15 September 2006 15:21 > To: xen-users@lists.xensource.com > Subject: [Xen-users] 199% CPU in DomU > > Hi! > > We have a silly Problem, we are using xen on 6 machines. Everything > works beautiful, but one DomU sometimes takes 199 percent of CPU an > hangs (says xm top). Only an xm destroy and recreate can > "reaktivate" it > again. Normally it takes only around 25-40 percent. Sometimes > it happens > 1 time per week but sometimes every day. There is no more load at > hangtime than normal and xen writes nothing to the logfiles > (DomU/Dom0).When this happens, can you access the DomU in question? Is it always the same DomU? What does "top" inside the DomU say? What OS are you running in DomU? -- Mats _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Hi, i have no solution for the hanging DomU, but 1 logical CPU = 100 Percent possible CPU-Load and 2 logical CPUs = 2 * 100 Percent possible CPU-Load = 200 Percent possible CPU-Load. Greetings, -timo On Fri, 15 Sep 2006 16:21:21 +0200, Felix Jaussi <fj@turtle-entertainment.de> wrote:> Hi! > > We have a silly Problem, we are using xen on 6 machines. Everything > works beautiful, but one DomU sometimes takes 199 percent of CPU an > hangs (says xm top). Only an xm destroy and recreate can "reaktivate" it > again. Normally it takes only around 25-40 percent. Sometimes it happens > 1 time per week but sometimes every day. There is no more load at > hangtime than normal and xen writes nothing to the logfiles (DomU/Dom0). > > We already changed the Dom0 System (we have an identical machine) and > the Kernel is the same as on the other Systems and was built without USB > Support. > > > Have anybody an idea where I have to search for a solution of this > Problem? Or anybody who already solved it? :-) > > Thanks for Help! > > Felix > > > Some system specs: > > Versions: xen-3.0.2-2 and xen-3.0-3.0.2+hg9697 (self compiled) > > Debian Sarge 64bit > Intel(R) Pentium(R) D CPU 3.40GHz > TYAN S5161 Mainboard > 4GB RAM (tested) > > XFS Filesystem (only) > > > 2.6.16.13-xen #2 SMP x86_64 GNU/Linux > > lspci > 0000:00:00.0 Host bridge: Intel Corporation E7230 Memory Controller Hub > (rev 81) > 0000:00:01.0 PCI bridge: Intel Corporation E7230 PCI Express Root Port > (rev 81) > 0000:00:1c.0 PCI bridge: Intel Corporation 82801G (ICH7 Family) PCI > Express Port 1 (rev 01) > 0000:00:1c.4 PCI bridge: Intel Corporation 82801GR/GH/GHM (ICH7 Family) > PCI Express Port 5 (rev 01) > 0000:00:1d.0 USB Controller: Intel Corporation 82801G (ICH7 Family) USB > UHCI #1 (rev 01) > 0000:00:1d.1 USB Controller: Intel Corporation 82801G (ICH7 Family) USB > UHCI #2 (rev 01) > 0000:00:1d.2 USB Controller: Intel Corporation 82801G (ICH7 Family) USB > UHCI #3 (rev 01) > 0000:00:1d.3 USB Controller: Intel Corporation 82801G (ICH7 Family) USB > UHCI #4 (rev 01) > 0000:00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev e1) > 0000:00:1f.0 ISA bridge: Intel Corporation 82801GB/GR (ICH7 Family) LPC > Interface Bridge (rev 01) > 0000:00:1f.1 IDE interface: Intel Corporation 82801G (ICH7 Family) IDE > Controller (rev 01) > 0000:00:1f.3 SMBus: Intel Corporation 82801G (ICH7 Family) SMBus > Controller (rev 01) > 0000:02:00.0 PCI bridge: Intel Corporation 6702PXH PCI Express-to-PCI > Bridge A (rev 09) > 0000:03:04.0 RAID bus controller: 3ware Inc 9550SX SATA-RAID > 0000:04:00.0 Ethernet controller: Intel Corporation 82573V Gigabit > Ethernet Controller (Copper) (rev 03) > 0000:0a:02.0 Ethernet controller: Intel Corporation 82557/8/9 [Ethernet > Pro 100] (rev 10) > 0000:0a:05.0 VGA compatible controller: XGI - Xabre Graphics Inc Volari Z7 > > > > > -- > Turtle Entertainment GmbH > Felix Jaussi, > Senior Systems Administrator > Technical Head of Events > Siegburger Str. 189 > 50679 Koeln > Germany > fon. +49 221 880449-312 > fax. +49 221 880449-399 > http://www.turtle-entertainment.de/ > > >-- Timo Benk - Jabber ID: fry@jabber.org - ICQ ID: #241877854 PGP Public Key: http://m28s01.vlinux.de/timo_benk_gpg_key.asc _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Hi, I have a similar problem with one of our DomUs. Just to narrow chances, is there nagios running on the 199% CPU-DomU? In my particular case, we narrowed down the processes to create that situation to the nagios-daemon. While this is running, the DomU happens to freeze - there is no connection possible neither ssh nor console. I''m hoping, anybody got a solution or some hints, what we can do. Thanks in advance, Tom --On 15. September 2006 16:21:21 +0200 Felix Jaussi <fj@turtle-entertainment.de> wrote:> Hi! > > We have a silly Problem, we are using xen on 6 machines. Everything > works beautiful, but one DomU sometimes takes 199 percent of CPU an > hangs (says xm top). Only an xm destroy and recreate can "reaktivate" it > again. Normally it takes only around 25-40 percent. Sometimes it happens > 1 time per week but sometimes every day. There is no more load at > hangtime than normal and xen writes nothing to the logfiles (DomU/Dom0). > > We already changed the Dom0 System (we have an identical machine) and > the Kernel is the same as on the other Systems and was built without USB > Support. > > > Have anybody an idea where I have to search for a solution of this > Problem? Or anybody who already solved it? :-) > > Thanks for Help! > > Felix > >_______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users
Hi, no we also have nagios (v1.3) running in one DomU but this one is runnig without any problem since months (with 60 servers to check). On saturday morning (23.09.06) we changed Dom0 to unstable and it''s running without problems until today (25.09.06). I''ll tell you about our experiences in a few days. But the unstable version seems to be very stable :-) Thanks for answering! Felix Thomas Schneider schrieb:> Hi, > > I have a similar problem with one of our DomUs. Just to narrow > chances, is there nagios running on the 199% CPU-DomU? > > In my particular case, we narrowed down the processes to create that > situation to the nagios-daemon. While this is running, the DomU > happens to freeze - there is no connection possible neither ssh nor > console. > > I''m hoping, anybody got a solution or some hints, what we can do. > > Thanks in advance, > > Tom > > --On 15. September 2006 16:21:21 +0200 Felix Jaussi > <fj@turtle-entertainment.de> wrote: > >> Hi! >> >> We have a silly Problem, we are using xen on 6 machines. Everything >> works beautiful, but one DomU sometimes takes 199 percent of CPU an >> hangs (says xm top). Only an xm destroy and recreate can "reaktivate" it >> again. Normally it takes only around 25-40 percent. Sometimes it happens >> 1 time per week but sometimes every day. There is no more load at >> hangtime than normal and xen writes nothing to the logfiles (DomU/Dom0). >> >> We already changed the Dom0 System (we have an identical machine) and >> the Kernel is the same as on the other Systems and was built without USB >> Support. >> >> >> Have anybody an idea where I have to search for a solution of this >> Problem? Or anybody who already solved it? :-) >> >> Thanks for Help! >> >> Felix >> >> > > > > _______________________________________________ > Xen-users mailing list > Xen-users@lists.xensource.com > http://lists.xensource.com/xen-users >-- Turtle Entertainment GmbH Felix Jaussi, Senior Systems Administrator Technical Head of Events Siegburger Str. 189 50679 Koeln Germany fon. +49 221 880449-312 fax. +49 221 880449-399 http://www.turtle-entertainment.de/ _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users