On 10/28/2013 01:30 PM, Yaodong Yang wrote:
Hi all,
When we migrate a vm from one host to another, we set the migrate_set_speed
200 inside the qemu monitor. What does the 200 means? Is it the maximum
migration speed is 200MB/s or something else?
This means the bandwidth limit is 200
On Thu, Oct 24, 2013 at 04:01:10PM +0900, MORITA Kazutaka wrote:
Currently, if a sheepdog server exits, all the connecting VMs need to
be restarted. This series implements a feature to reconnect the
server, and enables us to do online sheepdog upgrade and avoid
restarting VMs when sheepdog
Hi Alex,
I've been doing some testing with the latest git version and so far I haven't
seen a guest freeze in the same circumstances as before.
A weird thing that has been happening is the RTC timer stopping after a live
migration. This happened in both 1.6.1 and the 1.6.50 git build. To
On 10/21/2013 03:52 PM, Fedorov Sergey wrote:
On 10/21/2013 03:44 PM, Fedorov Sergey wrote:
On 04/23/2013 04:00 PM, Stefan Hajnoczi wrote:
On Tue, Apr 23, 2013 at 11:41:42AM +0400, Fedorov Sergey wrote:
Beyond that, we also want to avoid growing net queues
indefinitely. If
the hub does
On 28 Oct 2013, at 06:58, Matthew Anderson wrote:
I've been doing some testing with the latest git version and so far I haven't
seen a guest freeze in the same circumstances as before.
That's good news.
A weird thing that has been happening is the RTC timer stopping after a live
Hi,
do you know if it is possible to obtain the client machine id of a Windows
vServer via
a Hyper-V hypercall? I would need an information to check vServer activations
against
our KMS.
Thanks,
Peter
Hi,
diff --git a/ui/vnc.c b/ui/vnc.c
index 5601cc3..2177704 100644
--- a/ui/vnc.c
+++ b/ui/vnc.c
@@ -876,7 +876,8 @@ static int find_and_clear_dirty_height(struct VncState
*vs,
static int vnc_update_client_sync(VncState *vs, int has_dirty)
{
int ret = vnc_update_client(vs,
Hi,
Please post any comments or questions if you get around to testing them.
Your comments are very welcome!
Best regards,
-Gonglei
On 22.10.13 at 06:08, Gonglei (Arei) arei.gong...@huawei.com
wrote:
Hi, guys. The new patch has been modified based on the principles you
suggested,
On 28 Oct 2013, at 07:44, Alex Bligh wrote:
A weird thing that has been happening is the RTC timer stopping after a live
migration. This happened in both 1.6.1 and the 1.6.50 git build. To
replicate the issue I was migrating to/from the same machine and anywhere
between 1 and 3
On 10/11/13 19:54, Stefan Hajnoczi wrote:
On Thu, Sep 12, 2013 at 9:46 PM, Laszlo Ersek ler...@redhat.com wrote:
When qemu dies unexpectedly, for example in response to an explicit
abort() call, or (more importantly) when an external signal is delivered
to it that results in a coredump,
Hello Kevin Stefan
Any comments or wild guess about the bug?
Regards,
Jack
On 10/25/2013 05:01 PM, Jack Wang wrote:
Hi Experts,
We've seen guest block io lost in a VM.any response will be helpful
environment is:
guest os: Ubuntu 1304
running busy database workload with xfs on a disk
On 24.10.13 at 14:17, Gonglei (Arei) arei.gong...@huawei.com wrote:
Now I test the patch based on the codes of trunk, which works well.
The patch has been modified after your suggestion.
Partly. I looks reasonable now, but still not pretty. But the tools
maintainers will have to have the final
Hi,
Any comments will be welcome.
Best regards,
-Gonglei
-Original Message-
From: Gonglei (Arei)
Sent: Thursday, October 24, 2013 1:14 PM
To: qemu-devel@nongnu.org; 'Gerd Hoffmann'; 'Stefan Hajnoczi'
Cc: Luonengjun; Huangweidong (Hardware); Yanqiangjun
Subject: [PATCH] vnc: Fix
On 10/28/2013 10:54 AM, Alexey Zaytsev wrote:
Hey.
I very much doubt this commit could be causing the problem, as qemu
would never set wrong request type in the first place. You can easily
check by either reverting it, or adding a printk() before
Il 23/10/2013 14:16, Antony Pavlov ha scritto:
On Tue, 24 Sep 2013 08:32:10 +0400
Antony Pavlov antonynpav...@gmail.com wrote:
ping-ping
On Fri, 13 Sep 2013 11:33:24 +0400
Antony Pavlov antonynpav...@gmail.com wrote:
ping
Changes since v2:
* commit messages: drop ALL 'Reviewed-by'
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Il 21/10/2013 22:41, Eric Blake ha scritto:
On 10/21/2013 03:16 AM, Wenchao Xia wrote:
The define will be moved to qapi-schema.json later, so rename
the prefix to match its naming style.
Wouldn't it be simpler to fix the code generator to
Il 28/10/2013 07:58, Matthew Anderson ha scritto:
Hi Alex,
I've been doing some testing with the latest git version and so far I haven't
seen a guest freeze in the same circumstances as before.
A weird thing that has been happening is the RTC timer stopping after a live
migration. This
-Original Message-
From: Gerd Hoffmann [mailto:kra...@redhat.com]
Sent: Monday, October 28, 2013 3:53 PM
To: Gonglei (Arei)
Cc: qemu-devel@nongnu.org; Stefan Hajnoczi; Yanqiangjun; Luonengjun;
Huangweidong (Hardware)
Subject: Re: [Qemu-devel] [PATCH] vnc: Fix qemu crash on vnc
Le Friday 04 Oct 2013 à 16:35:18 (+0200), Max Reitz a écrit :
On 2013-10-02 14:39, Benoît Canet wrote:
Signed-off-by: Benoit Canet ben...@irqsave.net
---
block/quorum.c | 123
+
1 file changed, 123 insertions(+)
diff --git
Le Friday 04 Oct 2013 à 16:48:12 (+0200), Max Reitz a écrit :
On 2013-10-02 14:39, Benoît Canet wrote:
Use gnutls's SHA-256 to compare versions.
Wouldn't CRC32 suffice? (I don't really oppose using SHA, but taking
in gnutls as a dependency just for comparing several memory areas
seems a bit
Hey.
I very much doubt this commit could be causing the problem, as qemu
would never set wrong request type in the first place. You can easily
check by either reverting it, or adding a printk() before
virtio_blk_req_complete(VIRTIO_BLK_S_UNSUPP).
On Mon, Oct 28, 2013 at 10:15 AM, Jack Wang
Le Friday 04 Oct 2013 à 16:48:12 (+0200), Max Reitz a écrit :
On 2013-10-02 14:39, Benoît Canet wrote:
Use gnutls's SHA-256 to compare versions.
Wouldn't CRC32 suffice? (I don't really oppose using SHA, but taking
in gnutls as a dependency just for comparing several memory areas
seems a bit
This bug is still present in QEM 1.6.0 (qemu-system-x86 1.6.0+dfsg-1)
and/or Virtio 0.1-65.
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1119281
Title:
The virtio network device breaks
On 18:44 Fri 25 Oct , Peter Maydell wrote:
On 25 October 2013 12:04, Jean-Christophe PLAGNIOL-VILLARD
plagn...@jcrosoft.com wrote:
On 11:33 Sat 19 Oct , Jean-Christophe PLAGNIOL-VILLARD wrote:
as it's depend on current direction
ony change to get that applied?
Barebox relay
On 28 October 2013 13:24, Jean-Christophe PLAGNIOL-VILLARD
plagn...@jcrosoft.com wrote:
the register is supposed to report the status of the fifo
and in qemu if always report the datacnt which is the number of byte to
write and in case of reading it's always 0 so bootloader that use polling
Il 08/10/2013 02:41, Marcelo Tosatti ha scritto:
MAP_POPULATE mmap flag does not cause mmap to fail if allocation
of the entire area is not performed. HugeTLBfs performs reservation
of pages on a global basis: any further restriction to the reserved memory
such as cpusets placement or numa
On Sun, Oct 27, 2013 at 04:20:44PM +0100, igor Mammedov wrote:
Yes, thought of that, unfortunately its cumbersome to add an interface
for the user to supply both 2MB and 1GB hugetlbfs pages.
Could 2Mb tails be automated, meaning if host uses 1Gb hugepages and
there is/are tail/s, QEMU should
On Mon, Oct 28, 2013 at 12:04:06PM -0200, Marcelo Tosatti wrote:
On Sun, Oct 27, 2013 at 04:20:44PM +0100, igor Mammedov wrote:
Yes, thought of that, unfortunately its cumbersome to add an interface
for the user to supply both 2MB and 1GB hugetlbfs pages.
Could 2Mb tails be automated,
On 10/26/2013 11:37 AM, Xinyang Ge wrote:
External snapshots (via the blockdev-snapshot-sync QMP command) can be
taken in a matter of milliseconds if you only care about disk state.
Furthermore, if you want to take a snapshot of both memory and disk
state, such that the clone can be resumed
Le Saturday 26 Oct 2013 à 15:44:43 (+0200), Max Reitz a écrit :
bdrv_open_backing_file() tries to copy the backing file name using
pstrcpy directly after calling bdrv_open() to open the backing file
without checking whether that was actually successful. If it was not,
ps-backing_hd-file will
Le Thursday 24 Oct 2013 à 20:35:06 (+0200), Max Reitz a écrit :
Opening the qcow2 image with BDRV_O_NO_FLUSH prevents any flushes during
the image creation. This means that the image has not yet been flushed
to disk when qemu-img create exits. This flush is delayed until the next
operation on
Le Friday 25 Oct 2013 à 02:15:07 (+0200), Thibaut LAURENT a écrit :
Since commit 0ebd24e0a203cf2852c310b59fbe050190dc6c8c,
bdrv_open_common will throw an error when trying to open a file
read-only with the BDRV_O_COPY_ON_READ flag set.
Although BDRV_O_RDWR is unset for the backing files,
Hi list,
After a discussion on irc we have two potential solution in order to introduce
a new bs-node_name member in order to be able to manipulate the graph from the
monitors.
The first one is to make the QMP device parameter of the block commands optional
and add the node-name parameter as a
On 8 October 2013 01:41, Marcelo Tosatti mtosa...@redhat.com wrote:
+ret = sigaction(SIGBUS, oldact, NULL);
+if (ret) {
+perror(file_ram_alloc: fail to reinstall signal handler);
failed.
thanks
-- PMM
Stop/cont commands are broken with -icount due to a deadlock. The
real problem is that the computation of timers_state.cpu_ticks_offset
makes no sense with -icount enabled: we set it to an icount clock value
in cpu_disable_ticks, and subtract a TSC (or similar, whatever
cpu_get_real_ticks happens
Am 26.10.2013 um 15:44 hat Max Reitz geschrieben:
bdrv_open_backing_file() tries to copy the backing file name using
pstrcpy directly after calling bdrv_open() to open the backing file
without checking whether that was actually successful. If it was not,
ps-backing_hd-file will probably be
Am 25.10.2013 um 20:03 hat MORITA Kazutaka geschrieben:
At Wed, 23 Oct 2013 16:51:50 +0800,
Liu Yuan wrote:
v2:
- merge the reserved bits
This patch set makes use of copy_policy in struct SheepdogInode in order to
support recently introduced erasure coding volume in sheepdog.
Hi all,
this is some cleanup to the IDE code that I started long ago
and picked up again on my flight back from KVM Forum...
The patches clean up the callbacks to prepare for implementing request
retry for AHCI. After these patches, PIO retry should work for AHCI and
non-NCQ retry should be
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
block/blkdebug.c | 20
1 file changed, 20 insertions(+)
diff --git a/block/blkdebug.c b/block/blkdebug.c
index 16d2b91..4626c43 100644
--- a/block/blkdebug.c
+++ b/block/blkdebug.c
@@ -484,6 +484,25 @@ static
Make it optional and prepare for the next patches.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/atapi.c| 6 ++
hw/ide/core.c | 15 ---
hw/ide/internal.h | 1 +
3 files changed, 11 insertions(+), 11 deletions(-)
diff --git a/hw/ide/atapi.c
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
tests/libqtest.c | 7 ++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/tests/libqtest.c b/tests/libqtest.c
index 5205a43..6e42d01 100644
--- a/tests/libqtest.c
+++ b/tests/libqtest.c
@@ -129,11 +129,12 @@ QTestState
Using ide_start_dma instead of bmdma_start_dma introduces a new
assignment s-bus-dma-unit = s-unit. This introduces no
change because ide_handle_rw_error has already done the same
assignment.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/internal.h | 1 +
hw/ide/pci.c | 12
Drop the unused return value and make the callback optional.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 6 --
hw/ide/core.c | 5 +++--
hw/ide/internal.h | 3 ++-
hw/ide/macio.c| 1 -
hw/ide/pci.c | 4 +---
5 files changed, 6 insertions(+), 13
They are not used by AHCI, and should not be even available there.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/internal.h | 11 ---
hw/ide/pci.c | 4
hw/ide/pci.h | 7 +++
3 files changed, 11 insertions(+), 11 deletions(-)
diff --git
Drop the unused return value.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 2 +-
hw/ide/internal.h | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
index 265e3f2..b4b8386 100644
--- a/hw/ide/ahci.c
+++
Whenever an error stops the VM, ide_handle_rw_error does
s-bus-dma-unit = s-unit. So we can just use
idebus_active_if.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/pci.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/hw/ide/pci.c b/hw/ide/pci.c
index
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/cmd646.c | 3 +--
hw/ide/core.c | 5 +
hw/ide/internal.h | 1 +
hw/ide/piix.c | 3 +--
hw/ide/via.c | 3 +--
5 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/hw/ide/cmd646.c b/hw/ide/cmd646.c
index
AHCIDevice does not have a dma_status field. The add_status callback thus
does not make sense, start moving its functionality to new callbacks.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 12
hw/ide/atapi.c| 4 +++-
hw/ide/internal.h | 1 +
Drop the unused return value and make the callback optional.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 8
hw/ide/core.c | 5 +++--
hw/ide/internal.h | 2 +-
hw/ide/macio.c| 1 -
hw/ide/pci.c | 4 +---
5 files changed, 5 insertions(+), 15
Start moving the initial state of the current request to IDEBus, so that
AHCI can use it. The set_unit callback is not used anymore once this is
done.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 7 ---
hw/ide/core.c | 6 --
hw/ide/internal.h | 2 +-
It is now called only after the set_inactive callback. Put the two together.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 9 -
hw/ide/atapi.c| 2 +-
hw/ide/core.c | 12
hw/ide/internal.h | 6 +++---
hw/ide/macio.c| 1 -
Drop the unused return value and make the callback optional.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 4 +---
hw/ide/core.c | 10 +++---
hw/ide/internal.h | 3 +--
hw/ide/macio.c| 6 --
hw/ide/pci.c | 6 --
5 files changed, 5
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/pci.c | 28 ++--
1 file changed, 18 insertions(+), 10 deletions(-)
diff --git a/hw/ide/pci.c b/hw/ide/pci.c
index cc910de..c7fbe51 100644
--- a/hw/ide/pci.c
+++ b/hw/ide/pci.c
@@ -175,18 +175,24 @@ static void
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/core.c | 20 ++--
hw/ide/internal.h | 12 ++--
hw/ide/pci.c | 14 +++---
3 files changed, 23 insertions(+), 23 deletions(-)
diff --git a/hw/ide/core.c b/hw/ide/core.c
index a62654f..1e3108c
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/core.c | 66 -
hw/ide/internal.h | 2 ++
hw/ide/pci.c | 68 ---
hw/ide/pci.h | 1 -
4 files changed, 67
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/core.c | 2 +-
hw/ide/pci.c | 8
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/hw/ide/core.c b/hw/ide/core.c
index 93cfd46..5820fad 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -2195,7 +2195,7 @@ static
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
tests/ide-test.c | 74
1 file changed, 74 insertions(+)
diff --git a/tests/ide-test.c b/tests/ide-test.c
index 7307f1d..560dd2c 100644
--- a/tests/ide-test.c
+++ b/tests/ide-test.c
@@
This moves more common restarting logic to the core IDE code.
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/core.c | 6 ++
hw/ide/internal.h | 2 ++
hw/ide/pci.c | 15 ++-
hw/ide/pci.h | 4 ++--
4 files changed, 16 insertions(+), 11 deletions(-)
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/ahci.c | 5 -
hw/ide/core.c | 5 -
hw/ide/internal.h | 1 -
hw/ide/macio.c| 5 -
4 files changed, 16 deletions(-)
diff --git a/hw/ide/ahci.c b/hw/ide/ahci.c
index 1d4fb17..9cafee9 100644
--- a/hw/ide/ahci.c
+++
This only breaks backwards migration compatibility if the bus is in
an error state. It is in principle possible to avoid this by making
two subsections (one for version 1, and one for version 2, but with
the same name) with different _needed callbacks. The v1 callback would
return true if
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
hw/ide/atapi.c | 2 --
hw/ide/core.c | 3 +--
2 files changed, 1 insertion(+), 4 deletions(-)
diff --git a/hw/ide/atapi.c b/hw/ide/atapi.c
index 6b3f6c1..249b8b1 100644
--- a/hw/ide/atapi.c
+++ b/hw/ide/atapi.c
@@ -250,7 +250,6 @@ static void
This bug is still present in QEMU 1.6.0 (as per Debian's qemu-system-x86
1.6.0+dfsg-1 package).
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
https://bugs.launchpad.net/bugs/1119686
Title:
Incorrect handling of icebp
Status in
Public bug reported:
QEMU 1.5.0 (and git version, as far as I can tell from the source code)
has incorrect implementation of pmovzxbw and similar SSE4.1
instructions. The instruction zero-extends the first 8 8-bit elements of
a vector to 16bit vector and puts them to another vector. The current
Hi,
I try to add support for NBD in MinGW. Basicalyl this means adding support
for win32 sockets to aio-win32.c.
What I did was rewrite the file (attachment provided). problem here is that
revents for the node related to the nbd socket is always 0 after g_poll()
even when I see that data is
On Mon, Oct 28, 2013 at 05:43:16PM +0100, Paolo Bonzini wrote:
Hi all,
this is some cleanup to the IDE code that I started long ago
and picked up again on my flight back from KVM Forum...
The patches clean up the callbacks to prepare for implementing request
retry for AHCI. After these
Signed-off-by: Paolo Bonzini pbonz...@redhat.com
---
tests/libqtest.c | 10 +++---
tests/libqtest.h | 17 +++--
2 files changed, 18 insertions(+), 9 deletions(-)
diff --git a/tests/libqtest.c b/tests/libqtest.c
index bb82069..5205a43 100644
--- a/tests/libqtest.c
+++
Il 28/10/2013 18:16, Michael S. Tsirkin ha scritto:
On Mon, Oct 28, 2013 at 05:43:16PM +0100, Paolo Bonzini wrote:
Hi all,
this is some cleanup to the IDE code that I started long ago
and picked up again on my flight back from KVM Forum...
The patches clean up the callbacks to prepare for
External snapshots (via the blockdev-snapshot-sync QMP command) can be
taken in a matter of milliseconds if you only care about disk state.
Furthermore, if you want to take a snapshot of both memory and disk
state, such that the clone can be resumed from the same time, you can do
that with a
Ping.
r~
On 10/17/2013 08:29 AM, Richard Henderson wrote:
Changes from v2:
* Rebase for trivial conflicts
* Fix codingstyle errors
* Drop the static fallback code
* Use getauxval for AT_EXECFD
r~
Richard Henderson (6):
osdep: Create qemu_getauxval and qemu_init_auxval
On Mon, Oct 28, 2013 at 06:26:58PM +0100, Paolo Bonzini wrote:
Il 28/10/2013 18:16, Michael S. Tsirkin ha scritto:
On Mon, Oct 28, 2013 at 05:43:16PM +0100, Paolo Bonzini wrote:
Hi all,
this is some cleanup to the IDE code that I started long ago
and picked up again on my flight back
Il 28/10/2013 19:00, Michael S. Tsirkin ha scritto:
No, these are for another feature that is missing for AHCI, that is
support for stopping the VM on I/O errors. It is
https://bugzilla.redhat.com/show_bug.cgi?id=887844
Hmm. Actually maybe there was an io error... is there
an easy way
On Mon, Oct 28, 2013 at 07:36:32PM +0100, Paolo Bonzini wrote:
Il 28/10/2013 19:00, Michael S. Tsirkin ha scritto:
No, these are for another feature that is missing for AHCI, that is
support for stopping the VM on I/O errors. It is
https://bugzilla.redhat.com/show_bug.cgi?id=887844
Am 20.10.2013 18:39, schrieb Stefan Weil:
The latest configure invocation was saved in config-host.mak and could
be extracted from that file to recreate the configuration.
Now it is saved in a new file config.status which can be directly executed
to recreate the configuration. The file name
From: Alexander Graf ag...@suse.de
When AHCI executes an asynchronous IDE command, it checked DRDY without
checking either DRQ or BSY. This sometimes caused interrupt to be sent
before command is actually completed.
This resulted in a race condition: if guest then managed to access the
device
From: Alexander Graf ag...@suse.de
When AHCI executes an asynchronous IDE command, it checked DRDY without
checking either DRQ or BSY. This sometimes caused interrupt to be sent
before command is actually completed.
This resulted in a race condition: if guest then managed to access the
device
On Mon, Oct 28, 2013 at 09:00:15PM +0200, Michael S. Tsirkin wrote:
From: Alexander Graf ag...@suse.de
When AHCI executes an asynchronous IDE command, it checked DRDY without
checking either DRQ or BSY. This sometimes caused interrupt to be sent
before command is actually completed.
This
I would like to clarify about the support given to s390/s390x from QEMU.
Would you please give me an address where I can read about?
I'm curious about it. Up to now, I used Hercules to deploy z/OS... can I deploy
z/OS or z/VM directly under QEMU?
Thanks in advance,
Carlos
Am 18.09.2013 09:48, schrieb Jan Kiszka:
On 2013-09-18 09:26, Peter Maydell wrote:
[...]
And gcc's documentation of the 'noreturn' attribute specifically
says it does not affect the exceptional path where the function
returns via longjmp.
OK, that is the clarifying bit of information.
Now
MAP_POPULATE mmap flag does not cause mmap to fail if allocation of the
entire area is not performed. HugeTLBfs performs reservation of pages
on a global basis: any further restriction to the reserved memory such
as cpusets placement or numa node policy is performed at fault time
only.
Manually
v4: s/fail/failed/ (Peter Maydell)
---
MAP_POPULATE mmap flag does not cause mmap to fail if allocation of the
entire area is not performed. HugeTLBfs performs reservation of pages
on a global basis: any further restriction to the reserved memory such
as cpusets placement or numa node policy
I am trying to prevent write from DomU for particular sector of hardisk
which is passed through QEMU device.
I am putting an error condition in ide.c using API
ide_handle_write_error(s, -ret, BM_STATUS_ERROR) called from
ide_write_dma_cb, however DomU is still going ahead and writing to those
On 10/28/2013 12:09 PM, Carlos Morales wrote:
can I deploy z/OS or z/VM directly under QEMU?
No. QEMU's support is fairly Linux specific.
r~
Public bug reported:
If I run qemu user emulation with -L /path/to/my/sysroot/ in which also
the proc and dev filesystem is mounted QEMU eats my memory until it gets
killed by the kernel.
According to the strace output it follows the symbolic links in the proc
filesystem running forever in a
On 28 October 2013 23:15, Sebastian Macke sebast...@macke.de wrote:
If I run qemu user emulation with -L /path/to/my/sysroot/ in which also
the proc and dev filesystem is mounted QEMU eats my memory until it gets
killed by the kernel.
According to the strace output it follows the symbolic
Ok, thanks for the info.
For me it looks like removing the whole path code and putting a one-liner
combining two string is the best solution. But maybe I am missing something.
--
You received this bug notification because you are a member of qemu-
devel-ml, which is subscribed to QEMU.
On Mon, 10/28 16:40, Benoît Canet wrote:
Hi list,
After a discussion on irc we have two potential solution in order to introduce
a new bs-node_name member in order to be able to manipulate the graph from
the
monitors.
The first one is to make the QMP device parameter of the block
On Sun, 10/20 18:39, Stefan Weil wrote:
The latest configure invocation was saved in config-host.mak and could
be extracted from that file to recreate the configuration.
Now it is saved in a new file config.status which can be directly executed
to recreate the configuration. The file name
If the total number of the assigned numa nodes memory is not
equal to the assigned ram size, it will write the wrong data
to ACPI talb, then the guest will ignore the wrong ACPI table
and recognize all memory to one node. It's buggy, we should
check it to ensure that we write the right data to
Signed-off-by: Wanlong Gao gaowanl...@cn.fujitsu.com
---
Makefile.target | 2 +-
cpus.c | 14
include/sysemu/cpus.h | 1 -
include/sysemu/sysemu.h | 3 +
numa.c | 182
vl.c
The memory policy setting format is like:
policy={default|membind|interleave|preferred}[,relative=true],host-nodes=N-N
And we are adding this setting as a suboption of -numa mem,,
the memory policy then can be set like following:
-numa node,nodeid=0,cpus=0 \
-numa node,nodeid=1,cpus=1
As you know, QEMU can't direct it's memory allocation now, this may cause
guest cross node access performance regression.
And, the worse thing is that if PCI-passthrough is used,
direct-attached-device uses DMA transfer between device and qemu process.
All pages of the guest will be pinned by
Add the numa_info structure to contain the numa nodes memory,
VCPUs information and the future added numa nodes host memory
policies.
Reviewed-by: Eduardo Habkost ehabk...@redhat.com
Signed-off-by: Andre Przywara andre.przyw...@amd.com
Signed-off-by: Wanlong Gao gaowanl...@cn.fujitsu.com
---
Signed-off-by: Wanlong Gao gaowanl...@cn.fujitsu.com
---
include/sysemu/sysemu.h | 3 +-
numa.c | 148 +++-
qapi-schema.json| 30 ++
vl.c| 11 +++-
4 files changed, 114 insertions(+), 78
Add qmp command query-numa to show guest NUMA information.
Reviewed-by: Luiz Capitulino lcapitul...@redhat.com
Signed-off-by: Wanlong Gao gaowanl...@cn.fujitsu.com
---
numa.c | 66
qapi-schema.json | 36
Add -numa mem, option like following as Paolo suggested:
-numa mem,nodeid=0,size=1G
This new option will make later coming memory hotplug better.
We will use the new options to specify nodes memory info,
and just remain -numa node,mem=xx as legacy.
Reviewed-by: Laszlo Ersek
Set the guest numa nodes memory policies using the mbind(2)
system call node by node.
After this patch, we are able to set guest nodes memory policies
through the QEMU options, this arms to solve the guest cross
nodes memory access performance issue.
And as you all know, if PCI-passthrough is
libnuma choosed 128 for MAX_NODES, so we follow libnuma here.
Signed-off-by: Wanlong Gao gaowanl...@cn.fujitsu.com
---
include/sysemu/sysemu.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index 861cd77..995cf3b 100644
---
Reviewed-by: Luiz Capitulino lcapitul...@redhat.com
Signed-off-by: Wanlong Gao gaowanl...@cn.fujitsu.com
---
hmp.c | 57 +
hmp.h | 1 +
monitor.c | 21 +
3 files changed, 59 insertions(+), 20 deletions(-)
diff
Signed-off-by: Wanlong Gao gaowanl...@cn.fujitsu.com
---
qapi-schema.json | 19 ++-
1 file changed, 18 insertions(+), 1 deletion(-)
diff --git a/qapi-schema.json b/qapi-schema.json
index b7f0b15..a19e453 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -4198,7 +4198,8 @@
Public bug reported:
I don't know the commit tags but I checked out dtc on the 28 of october
at 20:27 in the tree of qemu (also git checkout out tonight). The
compilation fail at line 234 in qemu/dtc/Makefile so I inserted that
line:
@$ /usr/bin/strace -o /usr/src/qemu_build/error.log.txt
1 - 100 of 102 matches
Mail list logo
