Re: [PATCH 5/5] ioeventfd: Introduce KVM_IOEVENTFD_FLAG_SOCKET

On Wed, 2011-07-06 at 20:58 +0300, Michael S. Tsirkin wrote: > On Wed, Jul 06, 2011 at 06:01:46PM +0300, Sasha Levin wrote: > > On Wed, 2011-07-06 at 14:42 +0300, Michael S. Tsirkin wrote: > > > On Wed, Jul 06, 2011 at 07:37:58AM +0300, Sasha Levin wrote: > > > > + if (p->sock) { > > > > +

Re: [PATCH] x86: Raise the hard VCPU count limit

On Sat, Jul 9, 2011 at 3:25 PM, Sasha Levin wrote: > The patch raises the hard limit of VCPU count to 1024. > > This will allow developers to easily work on scalability > and will allow users to test high VCPU setups easily without > patching the kernel. > > To prevent possible issues with current

[PATCH 5/9] kvm tools, qcow: Delayed L1 table writeout

This patch moves L1 table writeout to qcow_disk_flush(). The rationale here is that while writes to clusters that don't have L2 table allocated on-disk are volatile until VIRTIO_BLK_T_FLUSH is issued, we never corrupt the disk image. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad J

[PATCH 4/9] kvm tools, qcow: Introduce qcow_disk_flush()

This patch introduces a QCOW specific qcow_disk_flush() in preparation for delaying QCOW metadata writeout until VIRTIO_BLK_T_FLUSH time. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad Joshi Cc: Sasha Levin Signed-off-by: Pekka Enberg --- tools/kvm/disk/qcow.c | 22 ++

[PATCH 9/9] kvm tools, qcow: Flush only dirty L2 tables

This patch improves qcow_l2_cache_write() to only flush dirty L2 tables. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad Joshi Cc: Sasha Levin Signed-off-by: Pekka Enberg --- tools/kvm/disk/qcow.c| 11 ++- tools/kvm/include/kvm/qcow.h |1 + 2 files changed,

[PATCH 6/9] kvm tools, qcow: Don't fdatasync() L2 table writeout

There's now now point in making sure new L2 tables actually hit the disk before we write out data to clusters because they are not visible on-disk until qcow_disk_flush() is called which flushes the L1 table. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad Joshi Cc: Sasha Levin Si

[PATCH 3/9] kvm tools, qcow: Fix locking issues

The virtio_blk_do_io() function can enter the QCOW code through disk_image__{read,write,flush}() from multiple threads because it uses a thread pool for I/O requests. Thus, use locking to make the QCOW2 code thread-safe. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad Joshi Cc: Sas

[PATCH 7/9] kvm tools, qcow: Use big endian order for L2 table entries

Don't keep the in-memory array in CPU byte order to simplify delayed L2 table writeout. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad Joshi Cc: Sasha Levin Signed-off-by: Pekka Enberg --- tools/kvm/disk/qcow.c | 11 +++ 1 files changed, 3 insertions(+), 8 deletions(-

[PATCH 2/9] kvm tools, qcow: Use 'struct qcow_l2_table' instead of untyped array

This patch converts disk/qcow.c to use 'struct qcow_l2_table' for tracking dirty L2 tables later on in this series. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad Joshi Cc: Sasha Levin Signed-off-by: Pekka Enberg --- tools/kvm/disk/qcow.c | 80 ++--

[PATCH 8/9] kvm tools, qcow: Delayed L2 table writeout

This patch delays writeout for new L2 tables like we do for L1 tables. If a L2 table has non-allocated clusters, we mark that in the in-memory L2 table but don't actually write it to disk until the L2 table is thrown out of LRU cache or when qcow_disk_flush() is called. That makes writes to new clu

[PATCH 1/9] kvm tools, qcow: Rename struct qcow_l2_cache to struct qcow_l2_table

This patch renames 'struct qcow_l2_cache' to 'struct qcow_l2_table' in preparation for replacing the untyped L2 table arrays with the struct. Cc: Asias He Cc: Cyrill Gorcunov Cc: Ingo Molnar Cc: Prasad Joshi Cc: Sasha Levin Signed-off-by: Pekka Enberg --- tools/kvm/disk/qcow.c| 32

[PATCH 0/9] kvm tools, qcow: Improve QCOW performance

This series fixes QCOW locking issues and implements delayed metadata writeout. This improves performance of writeout to QCOW2 images that don't have clusters and L2 tables allocated on-disk. I tested the series by running mount -t ext4 /dev/vdb /mnt dd if=/dev/zero of=/mnt/tmp in the guest

[PATCH] x86: Raise the hard VCPU count limit

The patch raises the hard limit of VCPU count to 1024. This will allow developers to easily work on scalability and will allow users to test high VCPU setups easily without patching the kernel. To prevent possible issues with current setups, KVM_CAP_NR_VCPUS now returns the recommended VCPU limit

Re: guest suspend/resume & virtio: vring errors

On Sat, Jul 09, 2011 at 03:54:04PM +0400, Michael Tokarev wrote: > 09.07.2011 14:36, Gleb Natapov wrote: > > On Sat, Jul 09, 2011 at 02:09:46PM +0400, Michael Tokarev wrote: > > >>> Heh. Is this S4 or S3 suspend resume? Looks like recent breakage. > >>> The only knows problem to me is in win7/2008

Re: guest suspend/resume & virtio: vring errors

09.07.2011 14:36, Gleb Natapov wrote: > On Sat, Jul 09, 2011 at 02:09:46PM +0400, Michael Tokarev wrote: >>> Heh. Is this S4 or S3 suspend resume? Looks like recent breakage. >>> The only knows problem to me is in win7/2008 S3 resume + net. >> >> How can I know if it's S3 or S4? And I can't say i

Re: guest suspend/resume & virtio: vring errors

On Sat, Jul 09, 2011 at 02:09:46PM +0400, Michael Tokarev wrote: > 09.07.2011 13:55, Gleb Natapov wrote: > > On Sat, Jul 09, 2011 at 01:47:25PM +0400, Michael Tokarev wrote: > >> 09.07.2011 13:17, Gleb Natapov wrote: > > >> This means that neither in-guest suspend/resume nor > >> qemu-kvm migrate-

Re: guest suspend/resume & virtio: vring errors

09.07.2011 13:55, Gleb Natapov wrote: > On Sat, Jul 09, 2011 at 01:47:25PM +0400, Michael Tokarev wrote: >> 09.07.2011 13:17, Gleb Natapov wrote: >> This means that neither in-guest suspend/resume nor >> qemu-kvm migrate-to-file (which fails for a different >> reason I'm trying to debug now) works

Re: [PATCH net-next] skbuff: clear tx zero-copy flag

From: Shirley Ma Date: Sat, 09 Jul 2011 00:12:46 -0700 > This patch clears tx zero-copy flag as needed. > > Signed-off-by: Shirley Ma Applied, thanks. -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at

Re: guest suspend/resume & virtio: vring errors

On Sat, Jul 09, 2011 at 01:47:25PM +0400, Michael Tokarev wrote: > 09.07.2011 13:17, Gleb Natapov wrote: > > On Fri, Jul 08, 2011 at 11:02:54PM +0400, Michael Tokarev wrote: > >> I tried suspend/resume cycle for a linux guest > >> today, with 100% failure result. There are 2 > > Good. It works as

Re: guest suspend/resume & virtio: vring errors

09.07.2011 13:17, Gleb Natapov wrote: > On Fri, Jul 08, 2011 at 11:02:54PM +0400, Michael Tokarev wrote: >> I tried suspend/resume cycle for a linux guest >> today, with 100% failure result. There are 2 > Good. It works as expect :) Linux virtio drivers do not support PM. This means that neither

Re: guest suspend/resume & virtio: vring errors

On Fri, Jul 08, 2011 at 11:02:54PM +0400, Michael Tokarev wrote: > I tried suspend/resume cycle for a linux guest > today, with 100% failure result. There are 2 Good. It works as expect :) Linux virtio drivers do not support PM. > With e1000 instead of virtio-net-pci, the suspend > does not compl

[PATCH net-next] skbuff: clear tx zero-copy flag

Hello Dave, This patch clears tx zero-copy flag as needed. Sign-off-by: Shirley Ma --- net/core/skbuff.c |3 +++ 1 files changed, 3 insertions(+), 0 deletions(-) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index a9577a2..d220119 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.