Marcin Mirosław
2011-May-04 14:08 UTC
[Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
Hello!
I''m hitted by issue described there:
http://lists.xensource.com/archives/html/xen-devel/2010-09/msg00164.html
. I''m using 32bit guest (no SMP) on 64 xen-server. On hardened-kernel
(grsec)-2.6.{35,36} there is silence in dmesg (i don''t remember what
was
going on on earlier kernels). On hardened-kernel-2.6.{37,38} and on
vanilla-kernel-2.6.{37,38,39} and git-sources-2.6.39_rc5-r7 problem exists.
Here is link to gentoo bugzilla entry: http://bugs.gentoo.org/358549 .
If any information could be usefull please let me know.
Thanks for help!
Marcin
[ 71.870518] ------------[ cut here ]------------
[ 71.870529] WARNING: at block/blk-core.c:239 blk_start_queue+0x20/0x32()
[ 71.870532] Modules linked in: iptable_filter xt_iprange tun sit tunnel4
xt_TCPMSS ip6table_mangle nf_conntrack_ipv6 nf_defrag_ipv6 xt_state ip6t_rt
ip6table_filter xt_owner xt_NFQUEUE xt_multiport xt_mark xt_hashlimit
xt_connmark ip6_tables fuse usbcore
[ 71.870578] Pid: 0, comm: swapper Tainted: G W
2.6.39-rc5-git7 #1
[ 71.870581] Call Trace:
[ 71.870588] [<c1025763>] warn_slowpath_common+0x65/0x7a
[ 71.870593] [<c10f2879>] ? blk_start_queue+0x20/0x32
[ 71.870598] [<c1025787>] warn_slowpath_null+0xf/0x13
[ 71.870602] [<c10f2879>] blk_start_queue+0x20/0x32
[ 71.870608] [<c116b4ba>] kick_pending_request_queues+0x1c/0x2a
[ 71.870613] [<c116b68d>] blkif_interrupt+0x1c5/0x1db
[ 71.870619] [<c104a6ec>] handle_irq_event_percpu+0x28/0x114
[ 71.870624] [<c104a7f4>] handle_irq_event+0x1c/0x28
[ 71.870628] [<c104bc39>] handle_fasteoi_irq+0x59/0x6f
[ 71.870633] [<c113dc93>] __xen_evtchn_do_upcall+0x10f/0x198
[ 71.870638] [<c113ea11>] xen_evtchn_do_upcall+0x19/0x27
[ 71.870644] [<c1237197>] xen_do_upcall+0x7/0xc
[ 71.870650] [<c104007b>] ? posix_clock_release+0x23/0x35
[ 71.870655] [<c10013a7>] ? hypercall_page+0x3a7/0x1000
[ 71.870660] [<c1004cd7>] ? xen_safe_halt+0x12/0x1d
[ 71.870665] [<c100b77d>] default_idle+0x2c/0x4c
[ 71.870670] [<c1005eae>] cpu_idle+0x74/0x8e
[ 71.870676] [<c122edba>] rest_init+0x52/0x54
[ 71.870680] [<c133c668>] start_kernel+0x29d/0x2a4
[ 71.870685] [<c133c076>] i386_start_kernel+0x65/0x67
[ 71.870690] [<c133d42e>] xen_start_kernel+0x568/0x570
[ 71.870693] ---[ end trace 5c490816ac9331f5 ]---
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel
Konrad Rzeszutek Wilk
2011-May-05 21:22 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
On Wed, May 04, 2011 at 04:08:08PM +0200, Marcin Mirosław wrote:> Hello! > I''m hitted by issue described there: > http://lists.xensource.com/archives/html/xen-devel/2010-09/msg00164.html > . I''m using 32bit guest (no SMP) on 64 xen-server. On hardened-kernel > (grsec)-2.6.{35,36} there is silence in dmesg (i don''t remember what was > going on on earlier kernels). On hardened-kernel-2.6.{37,38} and on > vanilla-kernel-2.6.{37,38,39} and git-sources-2.6.39_rc5-r7 problem exists.Do you always get this when you try to mount a filesystem with barriers? And do you see this _only_ with 32-bit guests, but not with 64-bit ones?> Here is link to gentoo bugzilla entry: http://bugs.gentoo.org/358549 . > If any information could be usefull please let me know. > Thanks for help! > Marcin > > > > [ 71.870518] ------------[ cut here ]------------ > [ 71.870529] WARNING: at block/blk-core.c:239 blk_start_queue+0x20/0x32() > [ 71.870532] Modules linked in: iptable_filter xt_iprange tun sit tunnel4 > xt_TCPMSS ip6table_mangle nf_conntrack_ipv6 nf_defrag_ipv6 xt_state ip6t_rt > ip6table_filter xt_owner xt_NFQUEUE xt_multiport xt_mark xt_hashlimit > xt_connmark ip6_tables fuse usbcore > [ 71.870578] Pid: 0, comm: swapper Tainted: G W > 2.6.39-rc5-git7 #1 > [ 71.870581] Call Trace: > [ 71.870588] [<c1025763>] warn_slowpath_common+0x65/0x7a > [ 71.870593] [<c10f2879>] ? blk_start_queue+0x20/0x32 > [ 71.870598] [<c1025787>] warn_slowpath_null+0xf/0x13 > [ 71.870602] [<c10f2879>] blk_start_queue+0x20/0x32 > [ 71.870608] [<c116b4ba>] kick_pending_request_queues+0x1c/0x2a > [ 71.870613] [<c116b68d>] blkif_interrupt+0x1c5/0x1db > [ 71.870619] [<c104a6ec>] handle_irq_event_percpu+0x28/0x114 > [ 71.870624] [<c104a7f4>] handle_irq_event+0x1c/0x28 > [ 71.870628] [<c104bc39>] handle_fasteoi_irq+0x59/0x6f > [ 71.870633] [<c113dc93>] __xen_evtchn_do_upcall+0x10f/0x198 > [ 71.870638] [<c113ea11>] xen_evtchn_do_upcall+0x19/0x27 > [ 71.870644] [<c1237197>] xen_do_upcall+0x7/0xc > [ 71.870650] [<c104007b>] ? posix_clock_release+0x23/0x35 > [ 71.870655] [<c10013a7>] ? hypercall_page+0x3a7/0x1000 > [ 71.870660] [<c1004cd7>] ? xen_safe_halt+0x12/0x1d > [ 71.870665] [<c100b77d>] default_idle+0x2c/0x4c > [ 71.870670] [<c1005eae>] cpu_idle+0x74/0x8e > [ 71.870676] [<c122edba>] rest_init+0x52/0x54 > [ 71.870680] [<c133c668>] start_kernel+0x29d/0x2a4 > [ 71.870685] [<c133c076>] i386_start_kernel+0x65/0x67 > [ 71.870690] [<c133d42e>] xen_start_kernel+0x568/0x570 > [ 71.870693] ---[ end trace 5c490816ac9331f5 ]--- > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xensource.com > http://lists.xensource.com/xen-devel_______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Marcin Mirosław
2011-May-05 22:57 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
W dniu 2011-05-05 23:22, Konrad Rzeszutek Wilk pisze:> On Wed, May 04, 2011 at 04:08:08PM +0200, Marcin Mirosław wrote: >> Hello! >> I''m hitted by issue described there: >> http://lists.xensource.com/archives/html/xen-devel/2010-09/msg00164.html >> . I''m using 32bit guest (no SMP) on 64 xen-server. On hardened-kernel >> (grsec)-2.6.{35,36} there is silence in dmesg (i don''t remember what was >> going on on earlier kernels). On hardened-kernel-2.6.{37,38} and on >> vanilla-kernel-2.6.{37,38,39} and git-sources-2.6.39_rc5-r7 problem exists. > > Do you always get this when you try to mount a filesystem with > barriers? And do you see this _only_ with 32-bit guests, but not with 64-bit ones?I''m not admin of Dom0, i''ve got only one vm (with PV enabled), which is 32 bit. I didn''t try to start them with 64 bit kernel (and 32 bit userland), do you think it''s worth to try it? I don''t force barrier in fstab, on kernel hardened-2.6.36 (which doesn''t throws warnings), /proc/mounts shows barrier=1, there is in dmesg: [...] [ 0.209834] Initialising Xen virtual ethernet driver. [ 0.217792] blkfront: xvda: barriers enabled (tag) [...] On vanilla-2.6.39-rc5-git7 i''ve got in log: [ 6.505772] blkfront: xvda: empty write barrier op failed [ 6.505776] blkfront: xvda: barriers disabled (I hope i didn''t omit important part from dmesg, i didn''t want to paste tons of line) Regards. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Daniel Stodden
2011-May-05 23:03 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
On Thu, 2011-05-05 at 18:57 -0400, Marcin Mirosław wrote:> W dniu 2011-05-05 23:22, Konrad Rzeszutek Wilk pisze: > > On Wed, May 04, 2011 at 04:08:08PM +0200, Marcin Mirosław wrote: > >> Hello! > >> I''m hitted by issue described there: > >> http://lists.xensource.com/archives/html/xen-devel/2010-09/msg00164.html > >> . I''m using 32bit guest (no SMP) on 64 xen-server. On hardened-kernel > >> (grsec)-2.6.{35,36} there is silence in dmesg (i don''t remember what was > >> going on on earlier kernels). On hardened-kernel-2.6.{37,38} and on > >> vanilla-kernel-2.6.{37,38,39} and git-sources-2.6.39_rc5-r7 problem exists. > > > > Do you always get this when you try to mount a filesystem with > > barriers? And do you see this _only_ with 32-bit guests, but not with 64-bit ones? > > I''m not admin of Dom0, i''ve got only one vm (with PV enabled), which is > 32 bit. I didn''t try to start them with 64 bit kernel (and 32 bit > userland), do you think it''s worth to try it? > I don''t force barrier in fstab, on kernel hardened-2.6.36 (which doesn''t > throws warnings), /proc/mounts shows barrier=1, there is in dmesg: > [...] > [ 0.209834] Initialising Xen virtual ethernet driver. > [ 0.217792] blkfront: xvda: barriers enabled (tag) > [...] > > On vanilla-2.6.39-rc5-git7 i''ve got in log: > [ 6.505772] blkfront: xvda: empty write barrier op failed > [ 6.505776] blkfront: xvda: barriers disabled > > (I hope i didn''t omit important part from dmesg, i didn''t want to paste > tons of line)Iirc this stuff ultimately lead us to an irq migration bug. Are you running irqbalance? If so, can you turn it off and see if that helps? Daniel _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Marcin Mirosław
2011-May-05 23:07 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
W dniu 2011-05-06 01:03, Daniel Stodden pisze:> Iirc this stuff ultimately lead us to an irq migration bug. Are you > running irqbalance? If so, can you turn it off and see if that helps?No, i don''t run irqbalance daemon. IRQ options configured in kernel are: # zgrep -i "irq" /boot/config-2.6.36-hardened-r7 |grep -v "^#" CONFIG_GENERIC_HARDIRQS=y CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ=y CONFIG_GENERIC_IRQ_PROBE=y CONFIG_INLINE_SPIN_UNLOCK_IRQ=y CONFIG_INLINE_READ_UNLOCK_IRQ=y CONFIG_INLINE_WRITE_UNLOCK_IRQ=y CONFIG_HT_IRQ=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_HVC_IRQ=y CONFIG_TRACE_IRQFLAGS_SUPPORT=y # zgrep -i "irq" /boot/config-2.6.39-rc5-git7 |grep -v "^#" CONFIG_HAVE_IRQ_WORK=y CONFIG_IRQ_WORK=y CONFIG_HAVE_GENERIC_HARDIRQS=y CONFIG_GENERIC_HARDIRQS=y CONFIG_HAVE_SPARSE_IRQ=y CONFIG_GENERIC_IRQ_PROBE=y CONFIG_GENERIC_IRQ_SHOW=y CONFIG_IRQ_FORCED_THREADING=y CONFIG_INLINE_SPIN_UNLOCK_IRQ=y CONFIG_INLINE_READ_UNLOCK_IRQ=y CONFIG_INLINE_WRITE_UNLOCK_IRQ=y CONFIG_HT_IRQ=y CONFIG_SERIAL_8250_SHARE_IRQ=y CONFIG_SERIAL_8250_DETECT_IRQ=y CONFIG_HVC_IRQ=y CONFIG_TRACE_IRQFLAGS_SUPPORT=y _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Marcin Mirosław
2011-May-21 13:57 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
Hi! I''ve noticed kernel threads "flush-254:9" does 100%CPU utilization. Device 254-9 is logical volume created via LVM. I don''t know if this problem is related to earlier problem, but it happens on the same kernel as mentioned issue. Regards, Marcin. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Konrad Rzeszutek Wilk
2011-May-24 13:13 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
On Sat, May 21, 2011 at 03:57:13PM +0200, Marcin Mirosław wrote:> Hi! > I''ve noticed kernel threads "flush-254:9" does 100%CPU utilization. > Device 254-9 is logical volume created via LVM. > I don''t know if this problem is related to earlier problem, but it > happens on the same kernel as mentioned issue.What kernel? What is your dom0 kernel and your domU kernel? What is the LVM volume? Is it snapshot? Is it on top of a SATA device? SSD? Do give more details please. And what is ''bgo''? I presume a bugzilla, but you hadn''t provided a link. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Marcin Mirosław
2011-May-31 11:28 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
W dniu 24.05.2011 15:13, Konrad Rzeszutek Wilk pisze:> On Sat, May 21, 2011 at 03:57:13PM +0200, Marcin Mirosław wrote: >> Hi! >> I''ve noticed kernel threads "flush-254:9" does 100%CPU utilization. >> Device 254-9 is logical volume created via LVM. >> I don''t know if this problem is related to earlier problem, but it >> happens on the same kernel as mentioned issue. > > What kernel? What is your dom0 kernel and your domU kernel? What > is the LVM volume? Is it snapshot? Is it on top of a SATA device? > SSD?Unfortunately i can''t say much about dom0. Admin is very busy and didn''t answer me. I only know domU is placed at one logical volume (lvm). About domU: - i didn''t noticed any problem with kernels <2.6.37 - with kernels >=2.6.37 i noticed two problems, one of them is mentioned earlier (WARNING: at block/blk-core.c:239 blk_start_queue+0x20/0x32() ), second one is "100% of CPU utilization" - i''m not using lvm snapshot (or other features) - domU works as PV - zgrep -i xen /proc/config.gz CONFIG_XEN=y CONFIG_XEN_PVHVM=y CONFIG_XEN_MAX_DOMAIN_MEMORY=8 CONFIG_XEN_SAVE_RESTORE=y CONFIG_XEN_BLKDEV_FRONTEND=y CONFIG_XEN_NETDEV_FRONTEND=y CONFIG_HVC_XEN=y CONFIG_XEN_BALLOON=y CONFIG_XEN_DEV_EVTCHN=y CONFIG_XENFS=y CONFIG_XEN_COMPAT_XENFS=y CONFIG_XEN_SYS_HYPERVISOR=y CONFIG_XEN_PLATFORM_PCI=m ( kernel: 2.6.36-hardened-r9 ) - grep -i xen /usr/src/linux-2.6.38-hardened-r5/.config | grep -v "^#" CONFIG_XEN=y CONFIG_XEN_DOM0=y CONFIG_XEN_PRIVILEGED_GUEST=y CONFIG_XEN_PVHVM=y CONFIG_XEN_MAX_DOMAIN_MEMORY=128 CONFIG_XEN_SAVE_RESTORE=y CONFIG_PCI_XEN=y CONFIG_XEN_PCIDEV_FRONTEND=y CONFIG_XEN_BLKDEV_FRONTEND=y CONFIG_XEN_NETDEV_FRONTEND=y CONFIG_HVC_XEN=y CONFIG_XEN_BALLOON=y CONFIG_XEN_DEV_EVTCHN=y CONFIG_XEN_BACKEND=y CONFIG_XENFS=y CONFIG_XEN_COMPAT_XENFS=y CONFIG_XEN_SYS_HYPERVISOR=y CONFIG_XEN_XENBUS_FRONTEND=y CONFIG_XEN_PLATFORM_PCI=m CONFIG_SWIOTLB_XEN=y (problematic kernel)> Do give more details please.I''m sorry for inconvenience.> And what is ''bgo''? I presume a bugzilla, but you hadn''t provided > a link.This is gentoo bugzilla: http://bugs.gentoo.org/358549 Regards, Marcin _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Konrad Rzeszutek Wilk
2011-Jun-27 14:13 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
> (problematic kernel)I wonder if the reason for this are some other config options. Can you send the full config please?> > > Do give more details please. > > I''m sorry for inconvenience.When does this happend? From the bug it looks to be just happening during bootup, right?> > > And what is ''bgo''? I presume a bugzilla, but you hadn''t provided > > a link. > This is gentoo bugzilla: http://bugs.gentoo.org/358549Thank you. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Marcin Mirosław
2011-Jun-27 15:04 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
W dniu 27.06.2011 16:13, Konrad Rzeszutek Wilk pisze:> I wonder if the reason for this are some other config options. Can you send the > full config please?Yes, it''s attached. Config is from newer kernel but the same problems appears with it.> When does this happend? From the bug it looks to be just happening during bootup, right?Right, bug with "block/blk-core" appears very early. Bug "kernel threads "flush-254:9" does 100%CPU utilization" appears after a couple minutes of work. Sometimes it happens after 15 minuts. Regards, Marcin -- xmpp (jabber): marcin [at] mejor.pl _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Konrad Rzeszutek Wilk
2011-Jun-27 17:30 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
On Mon, Jun 27, 2011 at 05:04:30PM +0200, Marcin Mirosław wrote:> W dniu 27.06.2011 16:13, Konrad Rzeszutek Wilk pisze: > > I wonder if the reason for this are some other config options. Can you send the > > full config please? > > Yes, it''s attached. Config is from newer kernel but the same problems > appears with it. > > > When does this happend? From the bug it looks to be just happening during bootup, right? > > Right, bug with "block/blk-core" appears very early. Bug "kernel threadsOK, that is manifested in the DomU (PV guest) correct?> "flush-254:9" does 100%CPU utilization" appears after a couple minutes > of work. Sometimes it happens after 15 minuts.Ok, but that is in dom0 and I''ve no idea what gentoo is using as dom0 type patches. For that one I would need you to use the lastest Linux kernel (v3.0-rc4) and see if you get the same issue. _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel
Marcin Mirosław
2011-Jun-27 22:01 UTC
Re: [Xen-devel] Re: [b.g.o.358549] blkfront: Move blkif_interrupt into a tasklet.
W dniu 2011-06-27 19:30, Konrad Rzeszutek Wilk pisze:> On Mon, Jun 27, 2011 at 05:04:30PM +0200, Marcin Mirosław wrote: >> W dniu 27.06.2011 16:13, Konrad Rzeszutek Wilk pisze: >>> I wonder if the reason for this are some other config options. Can you send the >>> full config please? >> >> Yes, it''s attached. Config is from newer kernel but the same problems >> appears with it. >> >>> When does this happend? From the bug it looks to be just happening during bootup, right? >> >> Right, bug with "block/blk-core" appears very early. Bug "kernel threads > > OK, that is manifested in the DomU (PV guest) correct?All problems described by me manifests in DomU. I don''t have any access to dom0.>> "flush-254:9" does 100%CPU utilization" appears after a couple minutes >> of work. Sometimes it happens after 15 minuts. > > Ok, but that is in dom0 and I''ve no idea what gentoo is using as dom0 type > patches. For that one I would need you to use the lastest Linux kernel (v3.0-rc4) > and see if you get the same issue.No, problem with "flush thread" also manifests in DomU. On Dom0 is probalby used Centos, but don''t know nothing more:( . Those problems appear also on vanilla kernel 2.6.39_rc5-r7 , without any gentoo patches. I''ve tried 3.0.0-rc4, i''ve got twice time: [ 11.168744] ------------[ cut here ]------------ [ 11.168752] WARNING: at block/blk-core.c:239 blk_start_queue+0x1d/0x2d() [ 11.168755] Modules linked in: [ 11.168760] Pid: 0, comm: swapper Not tainted 3.0.0-rc4 #1 [ 11.168763] Call Trace: [ 11.168770] [<c1023387>] ? warn_slowpath_common+0x6a/0x7d [ 11.168774] [<c11014c7>] ? blk_start_queue+0x1d/0x2d [ 11.168778] [<c10233a7>] ? warn_slowpath_null+0xd/0x10 [ 11.168782] [<c11014c7>] ? blk_start_queue+0x1d/0x2d [ 11.168788] [<c1178f6a>] ? kick_pending_request_queues+0x19/0x27 [ 11.168792] [<c1179177>] ? blkif_interrupt+0x1ff/0x216 [ 11.168797] [<c104acf0>] ? handle_irq_event_percpu+0x1d/0x100 [ 11.168802] [<c100a737>] ? sched_clock+0x9/0xd [ 11.168806] [<c104adec>] ? handle_irq_event+0x19/0x25 [ 11.168811] [<c104c2fb>] ? handle_edge_irq+0x9b/0xb6 [ 11.168815] [<c114c4ef>] ? __xen_evtchn_do_upcall+0xf9/0x181 [ 11.168820] [<c114d25b>] ? xen_evtchn_do_upcall+0x16/0x23 [ 11.168824] [<c1242817>] ? xen_do_upcall+0x7/0xc [ 11.168829] [<c10013a7>] ? hypercall_page+0x3a7/0x1000 [ 11.168833] [<c1004b00>] ? xen_safe_halt+0xf/0x19 [ 11.168838] [<c100b31a>] ? default_idle+0x29/0x47 [ 11.168842] [<c1005c43>] ? cpu_idle+0x77/0x91 [ 11.168846] [<c134f625>] ? start_kernel+0x2a3/0x2a9 [ 11.168850] [<c13503a2>] ? xen_start_kernel+0x57b/0x583 [ 11.168853] ---[ end trace 7846c748fe8d32d4 ]--- [ 12.306076] usbcore: registered new interface driver usbfs [ 12.306086] usbcore: registered new interface driver hub [ 12.306604] usbcore: registered new device driver usb [ 12.414643] Adding 614396k swap on /dev/mapper/sda6--7-swap1. Priority:-1 extents:1 across:614396k [ 12.496706] Adding 511996k swap on /dev/mapper/sda6--7-swap2. Priority:-2 extents:1 across:511996k [ 14.521926] ip6_tables: (C) 2000-2006 Netfilter Core Team [ 27.803890] ------------[ cut here ]------------ [ 27.803898] WARNING: at block/blk-core.c:239 blk_start_queue+0x1d/0x2d() [ 27.803901] Modules linked in: tunnel4 xt_TCPMSS nf_conntrack_ipv6 nf_defrag_ipv6 ip6t_rt xt_state ip6table_mangle iptable_mangle iptable_nat nf_nat ip6table_filter ip6_tables iptable_filter xt_owner xt_NFQUEUE xt_multiport xt_mark xt_iprange xt_hashlimit xt_connmark usbcore [ 27.803948] Pid: 0, comm: swapper Tainted: G W 3.0.0-rc4 #1 [ 27.803951] Call Trace: [ 27.803957] [<c1023387>] ? warn_slowpath_common+0x6a/0x7d [ 27.803962] [<c11014c7>] ? blk_start_queue+0x1d/0x2d [ 27.803966] [<c10233a7>] ? warn_slowpath_null+0xd/0x10 [ 27.803971] [<c11014c7>] ? blk_start_queue+0x1d/0x2d [ 27.803977] [<c1178f6a>] ? kick_pending_request_queues+0x19/0x27 [ 27.803982] [<c1179177>] ? blkif_interrupt+0x1ff/0x216 [ 27.803988] [<c104acf0>] ? handle_irq_event_percpu+0x1d/0x100 [ 27.803993] [<c100a737>] ? sched_clock+0x9/0xd [ 27.803998] [<c104adec>] ? handle_irq_event+0x19/0x25 [ 27.804003] [<c104c2fb>] ? handle_edge_irq+0x9b/0xb6 [ 27.804008] [<c114c4ef>] ? __xen_evtchn_do_upcall+0xf9/0x181 [ 27.804013] [<c114d25b>] ? xen_evtchn_do_upcall+0x16/0x23 [ 27.804019] [<c1242817>] ? xen_do_upcall+0x7/0xc [ 27.804024] [<c10013a7>] ? hypercall_page+0x3a7/0x1000 [ 27.804029] [<c1004b00>] ? xen_safe_halt+0xf/0x19 [ 27.804033] [<c100b31a>] ? default_idle+0x29/0x47 [ 27.804038] [<c1005c43>] ? cpu_idle+0x77/0x91 [ 27.804043] [<c134f625>] ? start_kernel+0x2a3/0x2a9 [ 27.804048] [<c13503a2>] ? xen_start_kernel+0x57b/0x583 [ 27.804051] ---[ end trace 7846c748fe8d32d5 ]--- Full message.log is attached to gentoo''s bug. After 10-20 minutes and somi disk activity, kernel''s thread flush254:9 tries eat cpu (and load becomes over 10). When i run "sync" from console i''ve never goet console back. Sync doesn''t finish. For me nothings changed in newest kernel. Regards! _______________________________________________ Xen-devel mailing list Xen-devel@lists.xensource.com http://lists.xensource.com/xen-devel