Cc: qemu-sta...@nongnu.org
Signed-off-by: Gerd Hoffmann
---
hw/usb/hcd-xhci.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c
index 2e2eb55..10c938a 100644
--- a/hw/usb/hcd-xhci.c
+++ b/hw/usb/hcd-xhci.c
@@ -2123,6 +2123,7 @@ static TRBCCode xhci_disable_
Hi,
Here comes the usb patch queue. It brings bugfixes for xhci, uas and the
usb hub. Also some minor improvements and cleanups,
please pull,
Gerd
The following changes since commit 4ff78e0dbcd5c795962567fdc1b31e9e03c55b07:
Merge remote-tracking branch 'luiz/queue/qmp' into staging (201
Signed-off-by: Gerd Hoffmann
---
hw/usb/dev-uas.c | 15 ---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/hw/usb/dev-uas.c b/hw/usb/dev-uas.c
index 63ad12e..8701292 100644
--- a/hw/usb/dev-uas.c
+++ b/hw/usb/dev-uas.c
@@ -113,6 +113,9 @@ struct UASDevice {
QTAILQ
Cc: qemu-sta...@nongnu.org
Signed-off-by: Gerd Hoffmann
---
hw/usb/hcd-xhci.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c
index 4d693bc..3826979 100644
--- a/hw/usb/hcd-xhci.c
+++ b/hw/usb/hcd-xhci.c
@@ -1274,7 +1274,7 @@ static void x
Signed-off-by: Gerd Hoffmann
---
hw/usb/hcd-xhci.c | 19 +++
trace-events | 1 +
2 files changed, 20 insertions(+)
diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c
index 57c06e7..83161b9 100644
--- a/hw/usb/hcd-xhci.c
+++ b/hw/usb/hcd-xhci.c
@@ -586,6 +586,14 @@ static co
Signed-off-by: Gerd Hoffmann
---
hw/usb/hcd-xhci.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c
index be6b86e..57c06e7 100644
--- a/hw/usb/hcd-xhci.c
+++ b/hw/usb/hcd-xhci.c
@@ -1164,8 +1164,6 @@ static XHCIStreamContext *xhci_find_stream(XHCIEPContex
usb3 bulk endpoints with streams are implicitly pipelined now,
so the requests will actually be processed in parallel. Also
allow them to complete out-of-order.
Fixes stalls in the uas driver.
Cc: qemu-sta...@nongnu.org
Signed-off-by: Gerd Hoffmann
---
hw/usb/core.c | 7 ---
1 file changed
Respect the interval for interrupt endpoints, so we don't finish
transfers as fast as possible but at the rate configured by the guest.
Fixes guest deadlocks triggered by interrupt storms.
Cc:
Signed-off-by: Gerd Hoffmann
---
hw/usb/hcd-xhci.c | 44 +---
Signed-off-by: Gerd Hoffmann
---
hw/usb/dev-hub.c | 1 +
trace-events | 1 +
2 files changed, 2 insertions(+)
diff --git a/hw/usb/dev-hub.c b/hw/usb/dev-hub.c
index e865a98..54f63c0 100644
--- a/hw/usb/dev-hub.c
+++ b/hw/usb/dev-hub.c
@@ -475,6 +475,7 @@ static void usb_hub_handle_data(USBDe
Signed-off-by: Gerd Hoffmann
---
hw/usb/hcd-xhci.c | 2 +-
trace-events | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/usb/hcd-xhci.c b/hw/usb/hcd-xhci.c
index 83161b9..4d693bc 100644
--- a/hw/usb/hcd-xhci.c
+++ b/hw/usb/hcd-xhci.c
@@ -2135,7 +2135,6 @@ static TRBC
ack
On Mon, Sep 2, 2013 at 11:53 AM, Christophe Fergeau wrote:
> Several places in spice-core.c were using either g_malloc+snprintf
> or snprintf+g_strdup to achieve the same result as g_strdup_printf.
>
> Signed-off-by: Christophe Fergeau
> ---
> ui/spice-core.c | 22 --
>
From: Taimoor Mirza
port redirection code uses SO_REUSEADDR socket option before binding to
host port. Behavior of SO_REUSEADDR is different on Windows and Linux.
Relaunching QEMU with same host and guest port redirection values on Linux
throws error but on Windows it does not throw any error.
Pr
Hello. Here's one another pull request for the trivial patches queue.
The request comes somewhat out of order, but this is because I was at
a 3-week vacation and the trivial-patches queue hasn't been processed
during this time, and it accumulated a few patches which are pre-
dependences for furthe
From: "Michael R. Hines"
My bad - but it's very important for us to warn the user that
IPv6 is broken on RoCE in linux right now, until linux releases
a fixed version.
Signed-off-by: Michael R. Hines
Signed-off-by: Michael Tokarev
---
migration-rdma.c |8 +---
1 file changed, 5 insert
Am 30.08.2013 21:49, schrieb Eduardo Habkost:
> On Fri, Aug 30, 2013 at 04:51:20PM +0200, Andreas Färber wrote:
>> Am 27.08.2013 17:24, schrieb Eduardo Habkost:
>>> This is an attempt to make the CPUID cache topology code clearer, by
>>> replacing the magic numbers in the code with #defines, and mo
From: Peter Maydell
Some versions of clang will warn about adding integers to strings:
disas/i386.c:4753:23: error: adding 'char' to a string does not append
to the string [-Werror,-Wstring-plus-int]
oappend ("%es:" + intel_syntax);
~~~^~
disas/i386.c:4
From: Stefan Weil
Most typos were found using a modified version of codespell:
accross -> across
issueing -> issuing
TICNT_THRESHHOLD -> TICNT_THRESHOLD
bandwith -> bandwidth
VCARD_7816_PROPIETARY -> VCARD_7816_PROPRIETARY
occured -> occurred
gaurantee -> guarantee
sofware -> software
Signed-of
From: Stefan Weil
For existing libraries, pkg-config --cflags and pkg-config --libs won't
print error messages to stderr, so redirecting stderr is not necessary.
Signed-off-by: Stefan Weil
Signed-off-by: Michael Tokarev
---
configure | 36 ++--
1 file changed
Now that the memory subsystem is propagating the endianness correctly,
the ne2000 device should have its I/O ports marked as LITTLE_ENDIAN, as
PCI devices are little endian.
This makes the ne2000 NIC to work again on PowerPC.
Cc: qemu-sta...@nongnu.org
Cc: Stefan Hajnoczi
Signed-off-by: Aurelien
On Thu, Aug 29, 2013 at 02:09:29PM -0700, Richard Henderson wrote:
> Since FMT_timeval unconditionally uses %ld for both tv_sec and tv_usec,
> and already casts tv_usec to long, also cast tv_sec to long.
>
> Cc: Andreas Färber
> Signed-off-by: Richard Henderson
> ---
> qtest.c | 8
> 1
From: Stefan Weil
When a Python script is run, Python normally writes bytecode into a .pyc file.
QEMU's build process uses several Python scripts which are called from
configure or make.
The generated .pyc files take disk space without being of much use, because
those scripts are short, not time
On Thu, Aug 29, 2013 at 02:09:45PM -0700, Richard Henderson wrote:
> Signed-off-by: Richard Henderson
> ---
> tcg/i386/tcg-target.c | 41 +++--
> 1 file changed, 27 insertions(+), 14 deletions(-)
>
> diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c
>
From: Eric Blake
Per the qapi schema, block_set_io_throttle takes most arguments
as ints, not strings.
* qmp-commands.hx (block_set_io_throttle): Use correct type. Fix
whitespace and a copy-paste bug in the process.
Signed-off-by: Eric Blake
Reviewed-by: Benoit Canet
Signed-off-by: Michael T
From: Stefan Weil
Commit ac26eb69a311396668809eadbf7ff4e623447d4c added tcg_out64 to tcg/tcg.c.
tcg/tci/tcg-target.c already had a nearly identical implementation which is
now removed to fix a compiler error.
Signed-off-by: Stefan Weil
Reviewed-by: Richard Henderson
Signed-off-by: Michael Toka
From: Stefan Weil
These unimplemented opcodes are handled like illegal opcodes, but
they are used in existing code. We should at least report when they
are executed.
Signed-off-by: Stefan Weil
Reviewed-by: Peter Maydell
Signed-off-by: Michael Tokarev
---
target-arm/translate.c |4
1
From: Peter Maydell
"0xf << 28" shifts right into the sign bit, since 0xf is a signed
integer. Use the 'U' suffix to force an unsigned shift to avoid
this undefined behaviour and a clang sanitizer warning.
Signed-off-by: Peter Maydell
Reviewed-by: Eric Blake
Acked-by: Jan Kiszka
Signed-off-by
From: Antony Pavlov
If PFLASH_DEBUG is enabled then we have some build errors:
hw/block/pflash_cfi02.c: In function ‘pflash_timer’:
hw/block/pflash_cfi02.c:128:5: error: expected ‘)’ before string constant
hw/block/pflash_cfi02.c:128:5: error: too few arguments to function ‘fprintf’
This patch
From: Hervé Poussineau
This fixes the following assert when -device adlib is used:
ioport.c:240: portio_list_add: Assertion `pio->offset >= off_last' failed.
Signed-off-by: Hervé Poussineau
Signed-off-by: Michael Tokarev
---
hw/audio/adlib.c |2 +-
1 file changed, 1 insertion(+), 1 deleti
From: Alex Bligh
sleep() apparently doesn't exist under mingw. Use g_usleep for
portability.
Signed-off-by: Alex Bligh
Reviewed-by: Stefan Weil
Signed-off-by: Michael Tokarev
---
tests/test-aio.c |6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/tests/test-aio.c b/
From: Stefan Weil
Predicate options (--exists, --atleast-version, ...) of pkg-config dont't
print error messages to stderr, so redirecting stderr is not necessary.
Combining a predicate option with --modversion is not necessary for tests.
Instead of testing with --modversion, --exists can be use
From: Stefan Hajnoczi
Drop error code path which cannot be taken since qemu_bh_new() does not
return NULL.
Signed-off-by: Stefan Hajnoczi
Reviewed-by: Paolo Bonzini
Signed-off-by: Michael Tokarev
---
block/curl.c |6 --
1 file changed, 6 deletions(-)
diff --git a/block/curl.c b/bloc
Am 29.07.2013 02:26, schrieb Andreas Färber:
> Hello Michael and Gerd,
>
> As discussed, this series attempts to clean up PCIe devices fiddling with
> individual PCI VMStateFields. It is based on my qom-devices queue, containing
> changes to PCIe devices.
>
> v2 has been changed to use VMStateFie
Am 29.07.2013 04:03, schrieb Andreas Färber:
> Hello,
>
> Based on a comment from mst, this mini-series proposes to change semantics of
> VMStateDescription registration to be more similar to those of static
> properties.
>
> Today, a device has one VMStateDescription, the last assignment to dc-
On Mon, Jul 29, 2013 at 02:27:01AM +0200, Andreas Färber wrote:
> Use it conditional on msix_present() and drop msix_{save,load}() calls
> following pci_device_{save,load}().
>
> This reorders the msix_save() and msix_unuse_all_vectors() calls for
> virtio-pci, but they seem independent of each ot
On Mon, Jul 29, 2013 at 02:26:57AM +0200, Andreas Färber wrote:
> Drop the arguments to avoid QOM refactorings causing more churn.
>
> Signed-off-by: Andreas Färber
We discussed and discarded something very similar.
This only works correctly if you put it in a struct which has the pci
device at
On Mo, 2013-09-02 at 11:53 +0200, Christophe Fergeau wrote:
> Several places in spice-core.c were using either g_malloc+snprintf
> or snprintf+g_strdup to achieve the same result as g_strdup_printf.
Patch looks good but fails checkpatch.pl due to long lines.
cheers,
Gerd
On Mon, Jul 29, 2013 at 02:26:56AM +0200, Andreas Färber wrote:
> Drop the arguments to avoid QOM refactorings causing more churn.
>
> Signed-off-by: Andreas Färber
This discards compiler check that macro is used
appropriately and does not add a runtime check.
We discussed and discarded this ap
The following changes since commit 4ff78e0dbcd5c795962567fdc1b31e9e03c55b07:
Merge remote-tracking branch 'luiz/queue/qmp' into staging (2013-08-30
12:26:04 -0500)
are available in the git repository at:
git://github.com/stefanha/qemu.git net
for you to fetch changes up to e21f6f23606e90f
Am 02.09.2013 13:36, schrieb Michael S. Tsirkin:
> On Mon, Jul 29, 2013 at 02:26:57AM +0200, Andreas Färber wrote:
>> Drop the arguments to avoid QOM refactorings causing more churn.
>>
>> Signed-off-by: Andreas Färber
>
> We discussed and discarded something very similar.
Anthony requested that
From: Jan Kiszka
Each networking client has a queue for packets that could not yet be
delivered to that client. Calling this queue "send_queue" is highly
confusing as it has nothing to to with packets send from this client but
to it. Avoid this confusing by renaming it to "incoming_queue".
Signe
From: Vincenzo Maffione
This patch partially implements the e1000 interrupt mitigation mechanisms.
Using a single QEMUTimer, it emulates the ITR register (which is the newer
mitigation register, recommended by Intel) and approximately emulates
RADV and TADV registers. TIDV and RDTR register funct
From: Brad Smith
The following patch simplifies the *BSD tap/tun code and makes use of numbered
tap/tun interfaces on all *BSD OS's. NetBSD has a patch in their pkgsrc tree
to make use of this feature and DragonFly also supports this as well.
Signed-off-by: Brad Smith
Signed-off-by: Stefan Hajn
From: Brad Smith
This eliminates a warning about __packed being redefined as exposed by the
vmxnet3 code. __packed is not used anywhere in the vmxnet3 code.
CChw/net/vmxnet3.o
In file included from hw/net/vmxnet3.c:29:
hw/net/vmxnet3.h:37:1: warning: "__packed" redefined
In file included f
On Mon, Sep 02, 2013 at 03:06:08PM +0800, Liu Ping Fan wrote:
> note: I rebase it onto Stefan's net-next tree, since pc-1.7 has already been
> defined there.
I have just sent the pull request so it can be merged into
qemu.git/master.
Stefan
On Mon, Jul 29, 2013 at 04:03:56AM +0200, Andreas Färber wrote:
> Hello,
>
> Based on a comment from mst, this mini-series proposes to change semantics of
> VMStateDescription registration to be more similar to those of static
> properties.
>
> Today, a device has one VMStateDescription, the las
On Mon, Sep 02, 2013 at 01:38:25PM +0200, Andreas Färber wrote:
> Am 02.09.2013 13:36, schrieb Michael S. Tsirkin:
> > On Mon, Jul 29, 2013 at 02:26:57AM +0200, Andreas Färber wrote:
> >> Drop the arguments to avoid QOM refactorings causing more churn.
> >>
> >> Signed-off-by: Andreas Färber
> >
> > .name = "block_set_io_throttle",
> > -.args_type =
> > "device:B,bps:l,bps_rd:l,bps_wr:l,iops:l,iops_rd:l,iops_wr:l",
> > +.args_type =
> > "device:B,bps:l,bps_rd:l,bps_wr:l,iops:l,iops_rd:l,iops_wr:l,bps_max:l?,bps_rd_max:l?,bps_wr_max:l?,iops_max:l?,iops_rd_
On Sat, Aug 31, 2013 at 06:36:17PM -0400, Cole Robinson wrote:
> Unlike other list types, enum wasn't adding any padding, which caused
> a mismatch between the generated struct size and GenericList struct
> size. More details in a678e26cbe89f7a27cbce794c2c2784571ee9d21
>
> This crashed qemu if cal
This patchset implement continous leaky bucket throttling.
It use two requests queue to enable to do silly unbalanced throttling like
block_set_io_throttle 0 0 0 0 6000 1
It use two timer to get the timer callbacks and the throttle.c code simple
v12:
compute unit only when size > op_size [Fam
Implement the continuous leaky bucket algorithm devised on IRC as a separate
module.
Signed-off-by: Benoit Canet
---
include/qemu/throttle.h | 110 +
util/Makefile.objs |1 +
util/throttle.c | 396 +++
3 files changed, 50
The max parameter of the leaky bucket throttling algorithm can be used to
allow the guest to do bursts.
The max value is a pool of I/O that the guest can use without being throttled
at all. Throttling is triggered once this pool is empty.
Signed-off-by: Benoit Canet
---
block/qapi.c | 26 +
Signed-off-by: Benoit Canet
---
tests/Makefile|2 +
tests/test-throttle.c | 481 +
2 files changed, 483 insertions(+)
create mode 100644 tests/test-throttle.c
diff --git a/tests/Makefile b/tests/Makefile
index b0200fd..6d2f3ad 100644
Signed-off-by: Benoit Canet
---
block.c | 338 +
block/qapi.c | 21 ++-
blockdev.c| 102 +++---
include/block/block.h |1 -
include/block/block_int.h | 32 +
5 files changed, 165 i
This feature can be used in case where users are avoiding the iops limit by
doing jumbo I/Os hammering the storage backend.
Signed-off-by: Benoit Canet
---
block/qapi.c |3 +++
blockdev.c | 21 ++---
hmp.c|8 ++--
qapi-schema.json | 10 ++
The reference output for test case 026 hasn't been updated in a long
time and it's one of the "known failing" cases. This patch updates the
reference output so that unintentional changes can be reliably detected
again.
The problem with this test case is that it produces different output
depending
Ping,
I am aware that this patch must be a QObject/CPUState monstruosity but I don't
see how I could store the fact that the cpu derive from a "host" type cpu.
The alternative would be to remember a variable number of leaves and serving
them to the guest as needed but I don't find that much clean
On 1 July 2013 18:35, Peter Maydell wrote:
> From: Andreas Schwab
>
> This patch adds signal handling for AArch64. The code is based on the
> respective source in the Linux kernel.
Couple of minor things I noticed, and will fix for an upcoming v6:
> +typedef struct target_sigaltstack {
> +a
Hi. Can you elaborate why two CQs fix it? Does it depend on
HCA implementation?
I'm not against two CQs for sending and receiving. In fact I'm for it
because I use two CQs for postcopy RDMA support.
thanks,
On Fri, Aug 30, 2013 at 08:39:31PM +0800, Frank Yang wrote:
> When several VMs migrate wi
Hi All,
I am testing NPIV feature on upstream Qemu, I have configured the zone
and able to see the created vport on the storage array.
Since, I am learning on how to setup the NPIV, I haven't created the
different zone for
the vport and the array, I just added in the existing zone.
Now, how
Hi,
"target-i386:" please.
Am 27.08.2013 22:38, schrieb Benoît Canet:
> Some users running cpu intensive tasks checking the cache CPUID leaves at
> startup and making decisions based on the result reported that the guest was
> not reflecting the host CPUID leaves when -cpu host is used.
>
> This
I don't see the point of using hashes.
Using hashes means that at least one extra read will be done on the target to
compute the candidate target hash.
It's bad for a cloud provider where IOs count is a huge cost.
Another structure to replace a bitmap (smaller on the canonical case) would be
a bl
On Mon, Sep 02, 2013 at 05:38:42PM +0800, Guannan Ren wrote:
> usb-bot only supports 16 luns(0~15) and they must be contiguous,
> (using lun 0 and 2 without 1 doesn't work). In this case qemu
> doesn't throw an error, we can not find the lun 2 in guests. So
> Adding a checking function in libvirt t
On Mon, Sep 02, 2013 at 02:42:00PM +0200, Kevin Wolf wrote:
> diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check
> index 74628ae..42d6955 100755
> --- a/tests/qemu-iotests/check
> +++ b/tests/qemu-iotests/check
> @@ -239,12 +239,18 @@ do
> echo -n " [failed, exit status
On Mon, Sep 02, 2013 at 02:45:48PM +0200, Benoît Canet wrote:
>
> Ping,
>
> I am aware that this patch must be a QObject/CPUState monstruosity but I don't
> see how I could store the fact that the cpu derive from a "host" type cpu.
> The alternative would be to remember a variable number of leave
On Fri, Aug 30, 2013 at 08:28:29AM +0200, Peter Lieven wrote:
> Hi all,
>
> today I had the second incidence of a migrated system (copied with
> DD) to qemu which won't boot. (stuck after booting from harddisk
> message).
You should probably have looked at virt-v2v, but you are where you are
now,
Actually assuming it's a Linux guest, a third option would be:
(3) Use an external kernel + initrd:
guestfish -a disk.img -i
> download /boot/vmlinuz-... /tmp/kernel
> download /boot/initrd-... /tmp/initrd
qemu -kernel /tmp/kernel -initrd /tmp/initrd -hda disk.img ...
Rich.
--
Richard Jones,
Add an appropriate entry describing this event and its parameters into
qmp-events.txt.
Signed-off-by: Max Reitz
---
Follow-up to:
- Add metadata overlap checks (series, v5); particularly patch 2
(qcow2: Metadata overlap checks)
---
QMP/qmp-events.txt | 22 ++
1 file chang
Am 02.09.2013 um 14:58 hat Stefan Hajnoczi geschrieben:
> On Mon, Sep 02, 2013 at 02:42:00PM +0200, Kevin Wolf wrote:
> > diff --git a/tests/qemu-iotests/check b/tests/qemu-iotests/check
> > index 74628ae..42d6955 100755
> > --- a/tests/qemu-iotests/check
> > +++ b/tests/qemu-iotests/check
> > @@ -
On Mon, Sep 02, 2013 at 02:55:36PM +0200, Andreas Färber wrote:
[...]
> > diff --git a/target-i386/cpu.h b/target-i386/cpu.h
> > index 8a3d0fd..1ec32fa 100644
> > --- a/target-i386/cpu.h
> > +++ b/target-i386/cpu.h
> > @@ -865,6 +865,7 @@ typedef struct CPUX86State {
> > bool tsc_valid;
> >
Several places in spice-core.c were using either g_malloc+snprintf
or snprintf+g_strdup to achieve the same result as g_strdup_printf.
Signed-off-by: Christophe Fergeau
---
Changes since v1:
- split lines >80 chars (checkpatch.pl now succeeds)
ui/spice-core.c | 28 ++--
From: "Richard W.M. Jones"
Signed-off-by: Richard W.M. Jones
---
hw/pci-host/q35.c | 2 +-
include/hw/pci-host/q35.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/pci-host/q35.c b/hw/pci-host/q35.c
index 12314d8..9ed0a3d 100644
--- a/hw/pci-host/q35.c
+++ b/h
On Mon, Sep 02, 2013 at 01:36:19PM +0200, Gerd Hoffmann wrote:
> On Mo, 2013-09-02 at 11:53 +0200, Christophe Fergeau wrote:
> > Several places in spice-core.c were using either g_malloc+snprintf
> > or snprintf+g_strdup to achieve the same result as g_strdup_printf.
>
> Patch looks good but fails
On Mon, Sep 2, 2013 at 10:49 AM, Kevin Wolf wrote:
> From: Max Reitz
>
> Move the OFLAG_COPIED checks out of check_refcounts_l1 and
> check_refcounts_l2 and after the actual refcount checks/fixes (since the
> refcounts might actually change there).
>
> Signed-off-by: Max Reitz
> Signed-off-by: K
On 12 August 2013 16:39, Andreas Färber wrote:
> Am 12.08.2013 17:29, schrieb Jan Kiszka:
>> Accesses to unassigned io ports shall return -1 on read and be ignored
>> on write. Ensure these properties via dedicated ops, decoupling us from
>> the memory core's handling of unassigned accesses.
>>
>>
Hello All.
Nowdays i measured io performance with Virtio-Blk-Data-Plane.
There was something strange in test.
When vcpu count is 1, io performance is increased in test
But vcpu count is over 2, io performance is decreased in test.
i used 3.10.9 stable kernel, qemu(1.4.2) & fio 2.1
What should i
We are reliably seeing this post live-migration on an openstack
platform.
Setup:
hypervisor ==> Ubuntu 12.04.3 LTS
libvirt ===> 1.0.2-0ubuntu11.13.04.2~cloud0
qemu-kvm ===> 1.0+noroms-0ubuntu14.10
storage: NFS exports
Guest VM OS: Ubuntu 12.04.1 LTS and CentOS 6.4
We have ept enabled.
Sample ins
Hello All.
Nowdays i measured io performance with Virtio-Blk-Data-Plane.
There was something strange in test.
When vcpu count is 1, io performance is increased in test
But vcpu count is over 2, io performance is decreased in test.
i used 3.10.9 stable kernel, qemu(1.4.2) & fio 2.1
What should i
Hi All,
I am testing NPIV feature on upstream Qemu, I have configured the zone
and able to see the created vport on the storage array.
Since, I am learning on how to setup the NPIV, I haven't created the different
zone for
the vport and the array, I just added in the existing zone.
Now, how do
On Mon, Sep 02, 2013 at 02:14:36PM +0200, Benoît Canet wrote:
> This patchset implement continous leaky bucket throttling.
>
> It use two requests queue to enable to do silly unbalanced throttling like
> block_set_io_throttle 0 0 0 0 6000 1
>
> It use two timer to get the timer callbacks and the
Priority is used to make visible some subregions by obscuring
the parent MemoryRegion addresses overlapping with the subregion.
By allowing the priority to be negative the opposite can be done:
Allow a subregion to be visible on all the addresses not covered
by the parent MemoryRegion or other sub
Added a memory region that has negative priority and
extends over all the pci adddress space. This region will
"catch" all the accesses to the unassigned pci
addresses and it will be possible to emulate the
master abort scenario (When no device on the bus claims
the transaction).
Signed-off-by: Ma
The MemoryRegions assigned with this ops shall "intercept"
the accesses to unassigned pci address space and the
associated callback will set MASTER ABORT bit in the
STATUS register of the device that initiated the
transaction as defined in PCI spec.
Note: This implementation assumes that all the r
Note: The series is incomplete, for review only
PCI spec requires that a transaction that has not been claimed
by any PCI bus devices will be terminated by the initiator
with "master abort". For read transactions -1() is returned and
writes are silently dropped. (already implemented in qu
On 2 September 2013 15:13, Marcel Apfelbaum wrote:
> Note: The series is incomplete, for review only
>
> PCI spec requires that a transaction that has not been claimed
> by any PCI bus devices will be terminated by the initiator
> with "master abort". For read transactions -1() is returned
The moved OFLAG_COPIED check in qcow2_check_refcounts results in a
different output from test 039 (mismatches are now found after the
general refcount check (as far as any remain)). This patch adjusts the
expected test result accordingly.
Signed-off-by: Max Reitz
---
Follow-up to:
- Add metadata
On 2 September 2013 15:13, Marcel Apfelbaum wrote:
> Priority is used to make visible some subregions by obscuring
> the parent MemoryRegion addresses overlapping with the subregion.
>
> By allowing the priority to be negative the opposite can be done:
> Allow a subregion to be visible on all the
On Mon, 2013-09-02 at 15:30 +0100, Peter Maydell wrote:
> On 2 September 2013 15:13, Marcel Apfelbaum wrote:
> > Note: The series is incomplete, for review only
> >
> > PCI spec requires that a transaction that has not been claimed
> > by any PCI bus devices will be terminated by the initiator
> >
On 2 September 2013 15:13, Marcel Apfelbaum wrote:
> Added a memory region that has negative priority and
> extends over all the pci adddress space. This region will
> "catch" all the accesses to the unassigned pci
> addresses and it will be possible to emulate the
> master abort scenario (When no
On 2 September 2013 15:13, Marcel Apfelbaum wrote:
> +const MemoryRegionOps pci_unassigned_mem_ops = {
> +.valid.accepts = pci_unassigned_mem_accepts,
> +.endianness = DEVICE_NATIVE_ENDIAN,
> +};
This is wrong -- you want reads and writes to result in
your PCI-spec-defined behaviour, but
On 2 September 2013 15:39, Marcel Apfelbaum wrote:
> On Mon, 2013-09-02 at 15:30 +0100, Peter Maydell wrote:
>> On 2 September 2013 15:13, Marcel Apfelbaum wrote:
>> > Note: The series is incomplete, for review only
>> >
>> > PCI spec requires that a transaction that has not been claimed
>> > by
On Mon, 2013-09-02 at 15:38 +0100, Peter Maydell wrote:
> On 2 September 2013 15:13, Marcel Apfelbaum wrote:
> > Priority is used to make visible some subregions by obscuring
> > the parent MemoryRegion addresses overlapping with the subregion.
> >
> > By allowing the priority to be negative the o
On Mon, Sep 02, 2013 at 05:13:08PM +0300, Marcel Apfelbaum wrote:
> The MemoryRegions assigned with this ops shall "intercept"
> the accesses to unassigned pci address space and the
> associated callback will set MASTER ABORT bit in the
> STATUS register of the device that initiated the
> transacti
On Mon, 2013-09-02 at 17:48 +0300, Michael S. Tsirkin wrote:
> On Mon, Sep 02, 2013 at 05:13:08PM +0300, Marcel Apfelbaum wrote:
> > The MemoryRegions assigned with this ops shall "intercept"
> > the accesses to unassigned pci address space and the
> > associated callback will set MASTER ABORT bit
On Mon, Sep 02, 2013 at 05:18:13PM +0800, Wenchao Xia wrote:
> @@ -125,5 +125,39 @@ class TestFdSets(iotests.QMPTestCase):
> 'No file descriptor supplied via SCM_RIGHTS')
> self.vm.shutdown()
>
> +#Add fd at runtime, there are two ways: monitor related or fdset related
>
On Mon, Sep 02, 2013 at 05:18:10PM +0800, Wenchao Xia wrote:
> This series add test case for fd passing with unix socket at runtime. Since
> getfd and closefd interface will interact with monitor's data, so it will
> help to do regression test for monitor patches. Since python2 do not support
> sen
Some users running cpu intensive tasks checking the cache CPUID leaves at
startup and making decisions based on the result reported that the guest was
not reflecting the host CPUID leaves when -cpu host is used.
This patch fix this.
Signed-off-by: Benoit Canet
---
target-i386/cpu-qom.h |3 +
This patch uses directly cpuid_host to forward the informations instead of
storing a variable number of leaves in the cpu states.
v3:
s/i386/target-i386/ [Andrea]
move forward field to X86CPU structure and document it [Andrea]
rename forward field [Eduardo]
Rebase on top of eduardo ca
Am 02.09.2013 um 12:04 hat Max Reitz geschrieben:
> Add functionality for expanding zero clusters. This is necessary for
> downgrading the image version to one without zero cluster support.
>
> For non-backed images, this function may also just discard zero clusters
> instead of truly expanding th
Signed-off-by: Anthony PERARD
---
Right now, starting an HVM with Q35 chipset those not works because
HVMLoader (the Xen pre-bios) look for the standard chipset i440FX.
Especialy the PCI/ISA bridge.
Error message from HVMLoader:
assertion '(devfn != PCI_ISA_DEVFN) || ((vendor_id == 0x8086) &&
(
Signed-off-by: Anthony PERARD
---
hw/i386/pc_piix.c| 2 +-
include/hw/xen/xen.h | 4 +---
xen-all.c| 7 ---
3 files changed, 6 insertions(+), 7 deletions(-)
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 3c36a2a..a5ea582 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/
101 - 200 of 313 matches
Mail list logo
