On Wed, Jul 13, 2016 at 05:46:25PM +0200, Igor Mammedov wrote:
> On Wed, 13 Jul 2016 17:26:18 +0200
> Igor Mammedov wrote:
>
> > On Wed, 13 Jul 2016 12:04:44 -0300
> > Eduardo Habkost wrote:
> >
> > > On Wed, Jul 06, 2016 at 08:20:53AM +0200, Igor
Am 13.07.2016 um 17:30 schrieb goremykin:
> Andreas Färber писал 2016-07-12 18:41:
>> Am 12.07.2016 um 17:33 schrieb goremy...@ispras.ru:
>>> From: goremykin
>>>
>>> Option -dt-printf 'file' writes Device Tree (DiveceClass hierarchy) to
>>> 'file' using Json format. This
Hi,
Since 4840f10 "memory: let address_space_rw/ld*/st* run outside the
BQL", the ide-test /x86_64/ide/bmdma/no_busmaster hangs when qemu is
compiled with gthread coroutine . Is this a known issue?
(fwiw, running the test alone also crashes, with -p
/x86_64/ide/bmdma/no_busmaster, lacking
On 13 July 2016 at 16:30, goremykin wrote:
> We are developing automatic boards and device templates creation tools. It
> would be better if I get DeviceClass hierarchy without QEMU running, but
> it's unachievable due to implementation of QEMU device registration.
> External
* zhanghailiang (zhang.zhanghaili...@huawei.com) wrote:
> Usage:
> (qemu) migrate file:/path/to/vm_statefile
>
> Signed-off-by: zhanghailiang
> Signed-off-by: Benoit Canet
> ---
> - With this patch, we can easily test memory snapshot
> -
On Wed, 13 Jul 2016 11:59:29 -0300
Eduardo Habkost wrote:
> On Wed, Jul 06, 2016 at 08:20:54AM +0200, Igor Mammedov wrote:
> > first remove VCPU from exec loop and only then remove lapic.
> >
> > Signed-off-by: Chen Fan
> > Signed-off-by: Gu
On Wed, 13 Jul 2016 17:26:18 +0200
Igor Mammedov wrote:
> On Wed, 13 Jul 2016 12:04:44 -0300
> Eduardo Habkost wrote:
>
> > On Wed, Jul 06, 2016 at 08:20:53AM +0200, Igor Mammedov wrote:
> > > Signed-off-by: Igor Mammedov
> > >
Andreas Färber писал 2016-07-12 18:41:
Am 12.07.2016 um 17:33 schrieb goremy...@ispras.ru:
From: goremykin
Option -dt-printf 'file' writes Device Tree (DiveceClass hierarchy) to
'file' using Json format. This helps developers visualize the
hierarchy
of DeviceClass
On 07/13/2016 05:35 AM, Michael Rolnik wrote:
> a. a helper function sets a flag within env
... and exits the cpu loop.
> b. cpu_get_tb_cpu_state introduces this flag, though tb.flags, for code
> generation by gen_intermediate_code
> c. the code is generated
Yep.
> d. the flag remains to be
On Wed, 13 Jul 2016 12:04:44 -0300
Eduardo Habkost wrote:
> On Wed, Jul 06, 2016 at 08:20:53AM +0200, Igor Mammedov wrote:
> > Signed-off-by: Igor Mammedov
> > ---
> > target-i386/cpu.c | 1 +
> > 1 file changed, 1 insertion(+)
> >
> > diff --git
This bug was fixed in the package qemu - 2.0.0+dfsg-2ubuntu1.25
---
qemu (2.0.0+dfsg-2ubuntu1.25) trusty; urgency=medium
[Kai Storbeck]
* backport patch to fix guest hangs after live migration (LP: #1297218)
-- Serge Hallyn Fri, 01 Jul 2016 14:25:20
The verification of the Stable Release Update for qemu has completed
successfully and the package has now been released to -updates.
Subsequently, the Ubuntu Stable Release Updates Team is being
unsubscribed and will not receive messages about this bug report. In
the event that you encounter a
On Wed, Jul 06, 2016 at 08:20:54AM +0200, Igor Mammedov wrote:
> first remove VCPU from exec loop and only then remove lapic.
>
> Signed-off-by: Chen Fan
> Signed-off-by: Gu Zheng
> Signed-off-by: Zhu Guihua
>
On Wed, Jul 06, 2016 at 08:20:53AM +0200, Igor Mammedov wrote:
> Signed-off-by: Igor Mammedov
> ---
> target-i386/cpu.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/target-i386/cpu.c b/target-i386/cpu.c
> index 04c0b79..2fa445d 100644
> --- a/target-i386/cpu.c
>
On Mon, 11 Jul 2016 23:48:27 -0300
Eduardo Habkost wrote:
> On Wed, Jul 06, 2016 at 08:20:43AM +0200, Igor Mammedov wrote:
> > CPU added with device_add help won't have APIC ID set,
> > so set it according to socket/core/thread ids provided
> > with device_add command.
> >
On Wed, Jul 13, 2016 at 1:45 PM, Kevin Wolf wrote:
> Am 13.07.2016 um 13:33 hat Roman Penyaev geschrieben:
>> Just to be sure that we are on the same page:
>>
>> 1. We have this commit "linux-aio: Cancel BH if not needed" which
>>
>>a) introduces performance regression on my
On Wed, Jul 06, 2016 at 08:20:52AM +0200, Igor Mammedov wrote:
> object_property_add_child() silently fails with error that it can't
> create duplicate propery 'apic' as we already have 'apic' property
> registered for 'apic' feature. As result generic device_realize puts
> apic into unattached
On Wed, 13 Jul 2016 11:27:23 -0300
Eduardo Habkost wrote:
> On Wed, Jul 06, 2016 at 08:20:36AM +0200, Igor Mammedov wrote:
> > Igor Mammedov (19):
> > target-i386: cpu: use uint32_t for X86CPU.apic_id
> > pc: add x86_topo_ids_from_apicid()
> > pc: extract CPU lookup
On Wed, Jul 06, 2016 at 08:20:36AM +0200, Igor Mammedov wrote:
> Igor Mammedov (19):
> target-i386: cpu: use uint32_t for X86CPU.apic_id
> pc: add x86_topo_ids_from_apicid()
> pc: extract CPU lookup into a separate function
> pc: cpu: consolidate apic-id validity checks in
A future patch will add support for multiple gluster servers. Existing
terminology is a bit unusual in relation to what names are used by
other networked devices, and doesn't map very well to the terminology
we expect to use for multiple servers. Therefore, rename the following
options:
'server'
On Mon, Jul 11, 2016 at 08:28:46PM +0100, Dr. David Alan Gilbert (git) wrote:
> From: "Dr. David Alan Gilbert"
>
> Add the host-phys-bits boolean property, if true, take phys-bits
> from the hosts physical bits value, overriding either the default
> or the user specified
On 07/12/2016 05:17 PM, John Snow wrote:
>
>
> On 07/11/2016 03:50 PM, Colin Lord wrote:
>> Adds a new iotest for testing that the format probing functions work as
>> expected. This is done by booting up a vm with a disk image without
>> specifying the image format. Then the format is checked
unified coding styles of multiline function arguments and other error functions
moved random declarations of structures and other list variables
Signed-off-by: Prasanna Kumar Kalever
Reviewed-by: Eric Blake
Reviewed-by: Jeff Cody
This patch adds a way to specify multiple volfile servers to the gluster
block backend of QEMU with tcp|rdma transport types and their port numbers.
Problem:
Currently VM Image on gluster volume is specified like this:
file=gluster[+tcp]://host[:port]/testvol/a.img
Assuming we have three hosts
This version of patches are rebased on master branch.
Prasanna Kumar Kalever (4):
block/gluster: rename [server, volname, image] -> [host, volume, path]
block/gluster: code cleanup
block/gluster: using new qapi schema
block/gluster: add support for multiple gluster servers
v1:
multiple
This will be necessary in the next patch, which stops using atexit for
character devices; without it, vhost-user and the redirector filter
will cause a use-after-free. Relying on the ordering of atexit calls
is also brittle, even now that both the network and chardev
subsystems are using atexit.
On Wed, Jul 13, 2016 at 09:56:25AM +0200, Igor Mammedov wrote:
> On Tue, 12 Jul 2016 14:18:22 -0300
> Eduardo Habkost wrote:
>
> > On Tue, Jul 12, 2016 at 02:48:43PM +0200, Igor Mammedov wrote:
> > > On Tue, 12 Jul 2016 00:29:08 -0300
> > > Eduardo Habkost
this patch adds 'GlusterServer' related schema in qapi/block-core.json
Signed-off-by: Prasanna Kumar Kalever
---
block/gluster.c | 89 ++--
qapi/block-core.json | 67 ---
2
From: Marc-André Lureau
We would like to move back net_cleanup() at the end of main function,
like it used to be until f30dbae63a46f23116715dff8d130c, but minimum
tap cleanup is necessary regarless at exit() time. Use an exit notifier
to call TAP down_script. If
We would like to move back net_cleanup() at the end of main function,
like it used to be until f30dbae63a46f23116715dff8d130c, but minimum
cleanup is needed regardless at exit() time for slirp's SMB
functionality. Use an exit notifier to call slirp_smb_cleanup.
If net_cleanup() is called first,
From: Jarkko Lavinen
Scanners can provide additional sense bytes beyond 18 bytes.
VueScan uses 32 bytes alloc length with Request Sense command.
Signed-off-by: Jarkko Lavinen
Signed-off-by: Paolo Bonzini
---
From: Max Reitz
First, bdrv_open_child() expects all options for the child to be
prefixed by the child's name (and a separating dot). Second,
bdrv_open_child() does not take ownership of the QDict passed to it but
only extracts all options for the child, so if a QDict is
ping
On Sat, Jun 4, 2016 at 11:05 PM, wrote:
> From: Marc-André Lureau
>
> Hi
>
> vhost-user & virtio are not so simple and evolve regularly. There
> isn't a reference code that would help you get started either. And
> the backends
From: Xiao Guangrong
Currently, we use memory_region_is_mapped() to detect if the host
backend memory is being used. This works if the memory is directly
mapped into guest's address space, however, it is not true for
nvdimm as it uses aliased memory region to map
From: Fam Zheng
MIN_NON_ZERO(1, 0) is evaluated to 0. Rewrite the macro to fix it.
Reported-by: Miroslav Rezanina
Signed-off-by: Fam Zheng
Message-Id: <1468306113-847-1-git-send-email-f...@redhat.com>
Reviewed-by: Eric Blake
From: Marc-André Lureau
It turns out qemu is calling exit() in various places from various
threads without taking much care of resources state. The atexit()
cleanup handlers cannot easily destroy resources that are in use (by
the same thread or other).
Since
From: Marc-André Lureau
Commit 74b6ce43e3 uses the wrong free API for a SocketAddress, that
may leak some linked data.
Signed-off-by: Marc-André Lureau
Message-Id: <20160706164246.22116-1-marcandre.lur...@redhat.com>
Signed-off-by:
From: Jarkko Lavinen
Add support for missing scanner specific SCSI commands and their xfer
lenghts as per ANSI spec section 15.
Signed-off-by: Jarkko Lavinen
Signed-off-by: Paolo Bonzini
---
hw/scsi/scsi-bus.c | 31
From: Sean Bruno
The --quiet argument is not available on all operating systems. Use -s
instead to match the rest of the Makefile uses. This fixes a non-fatal
error seen on FreeBSD.
Reviewed-by: Eric Blake
Reviewed-by: Fam Zheng
The following changes since commit a91a4e7d8cfe6ece610aacf7c52738188f5b5cb5:
Merge remote-tracking branch 'remotes/ehabkost/tags/x86-pull-request' into
staging (2016-07-11 15:08:47 +0100)
are available in the git repository at:
git://github.com/bonzini/qemu.git tags/for-upstream
for you
From: Xiao Guangrong
'info memdev' crashes QEMU:
(qemu) info memdev
Unexpected error in parse_str() at qapi/string-input-visitor.c:111:
Parameter 'null' expects an int64 value or range
It is caused by null uint16List is returned if 'host-nodes' is the
Now that json-streamer tries not to leak tokens on incomplete parse,
the tokens can be freed twice if QEMU destroys the json-streamer
object during the parser->emit call. To fix this, create the new
empty GQueue earlier, so that it is already in place when the old
one is passed to parser->emit.
Ping.
On 04/07/2016 18:33, Paolo Bonzini wrote:
> This has better performance because it executes fewer system calls
> and does not use a bottom half per disk.
>
> Originally proposed by Ming Lei.
>
> Acked-by: Stefan Hajnoczi
> Signed-off-by: Paolo Bonzini
disas/arm-a64.cc is careful to include only the bare minimum that
it needs---qemu/osdep.h and disas/bfd.h. Unfortunately, disas/bfd.h
then includes qemu-common.h, which brings in qemu/option.h and from
there we get the kitchen sink.
This causes problems because for example QEMU's atomic macros
On Wed, Jul 13, 2016 at 2:22 PM, Eric Blake wrote:
> On 07/13/2016 01:57 AM, Roman Pen wrote:
>> v1..v2:
>>
>> o comment tweaks.
>> o fix QEMU coding style.
>
> The above comments should be delayed...
>
>>
>> Invoking io_setup(MAX_EVENTS) we ask kernel to create ring buffer
On Tue, Jul 5, 2016 at 11:19 AM, Peter Xu wrote:
> This patch enables interrupt remapping for PCI devices.
>
> To play the trick, one memory region "iommu_ir" is added as child region
> of the original iommu memory region, covering range 0xfeeX (which is
> the address range
From: Alberto Garcia
Throttling groups are named using the 'group' parameter of the
block_set_io_throttle command and the throttling.group command-line
option. If that parameter is unspecified the groups get the name of
the block device.
This patch adds a new test to check the
From: Cao jin
pointer 'qemu_aio_context' should be checked first before it is used.
qemu_bh_new() will use it.
Signed-off-by: Cao jin
Message-Id: <1467799740-26079-2-git-send-email-caoj.f...@cn.fujitsu.com>
Signed-off-by: Paolo Bonzini
From: Paolo Bonzini
In practice the entry argument is always known at creation time, and
it is confusing that sometimes qemu_coroutine_enter is used with a
non-NULL argument to re-enter a coroutine (this happens in
block/sheepdog.c and tests/test-coroutine.c). So pass the
Invoking io_setup(MAX_EVENTS) we ask kernel to create ring buffer for us
with specified number of events. But kernel ring buffer allocation logic
is a bit tricky (ring buffer is page size aligned + some percpu allocation
are required) so eventually more than requested events number is allocated.
From: Reda Sallahi
Commit "cdeaf1f vmdk: add bdrv_co_write_zeroes" causes a regression on
writes. It writes metadata after every write instead of doing it only once
for each cluster.
vmdk_pwritev() writes metadata whenever m_data is set as valid so this patch
sets m_data as
From: Marc Marí
This optionrom is based on linuxboot.S.
Signed-off-by: Marc Marí
Signed-off-by: Richard W.M. Jones
Message-Id: <1464027093-24073-2-git-send-email-rjo...@redhat.com>
[Add -fno-toplevel-reorder, support clang without -m16.
From: Max Reitz
iotest 157 pretends not to care about the image format used, but in fact
it does due to the format name not being filtered in its output. This
patch adds filtering and changes the reference output accordingly.
Signed-off-by: Max Reitz
From: Lin Ma
Currently qemu uses snapshot id to determine whether a snapshot is fully
available, It causes incorrect output in some scenario.
For instance:
(qemu) info block
drive_image1 (#block113): /opt/vms/SLES12-SP1-JeOS-x86_64-GM/disk0.qcow2
(qcow2)
Cache mode:
The following changes since commit a91a4e7d8cfe6ece610aacf7c52738188f5b5cb5:
Merge remote-tracking branch 'remotes/ehabkost/tags/x86-pull-request' into
staging (2016-07-11 15:08:47 +0100)
are available in the git repository at:
git://github.com/bonzini/qemu.git tags/for-upstream-fwcfg
Signed-off-by: Kevin Wolf
Reviewed-by: Max Reitz
---
tests/qemu-iotests/157 | 88 ++
tests/qemu-iotests/157.out | 22
tests/qemu-iotests/group | 1 +
3 files changed, 111 insertions(+)
create
From: Lin Ma
Currently, the output of 'info snapshots' shows fully available snapshots.
It's opaque, hides some snapshot information to users. It's not convenient
if users want to know more about all of snapshot information on every block
device via monitor.
Follow Kevin's and
From: Max Reitz
Emitting the plain error number is not very helpful. Use strerror()
instead.
Signed-off-by: Max Reitz
Message-id: 20160615153630.2116-2-mre...@redhat.com
Reviewed-by: Eric Blake
Signed-off-by: Max Reitz
From: Alberto Garcia
When I/O limits are set for a block device, the name of the throttling
group is taken from the BlockBackend if the user doesn't specify one.
Commit efaa7c4eeb7490c6f37f3 moved the naming of the BlockBackend in
blockdev_init() to the end of the function,
The rerror/werror policies are implemented in the devices, so that's
where they should be configured. In comparison to the old options in
-drive, the qdev properties are only added to those devices that
actually support them.
If the option isn't given (or "auto" is specified), the setting of the
From: Sascha Silbe
ratelimit_calculate_delay() previously reset the accounting every time
slice, no matter how much data had been processed before. This had (at
least) two consequences:
1. The minimum speed is rather large, e.g. 5 MiB/s for commit and stream.
Not
From: Max Reitz
We refuse to open images whose L1 table we deem "too big". Consequently,
we should not produce such images ourselves.
Cc: qemu-sta...@nongnu.org
Signed-off-by: Max Reitz
Message-id: 20160615153630.2116-3-mre...@redhat.com
Reviewed-by: Eric
Commit implemented the 'enospc' policy as 'ignore' if the error was not
ENOSPC. The QAPI documentation promises that it's treated as 'stop'.
Using the common block job error handling function fixes this and also
adds the missing QMP event.
Signed-off-by: Kevin Wolf
Reviewed-by:
As cache.writeback is a BlockBackend property and as such more related
to the guest device than the BlockDriverState, we already removed it
from the blockdev-add interface. This patch adds the new way to set it,
as a qdev property of the corresponding guest device.
For example: -drive
From: Alberto Garcia
This patch adds a new optional 'job-id' parameter to 'block-commit',
allowing the user to specify the ID of the block job to be created.
Signed-off-by: Alberto Garcia
Reviewed-by: Kevin Wolf
Reviewed-by: Max Reitz
From: Max Reitz
Recently, qcow2_get_cluster_offset() has been changed to work with bytes
instead of sectors. This invalidated some assertions and introduced a
possible integer multiplication overflow.
This could be reproduced using e.g.
$ qemu-img create -f qcow2 -o
werror/rerror are now available as qdev options. The stats-* options are
removed without an existing replacement; they should probably be
configurable with a separate QMP command like I/O throttling settings.
Removing id is left for another day because this involves updating
qemu-iotests cases to
From: Paolo Bonzini
CoQueue do not need to remove any element but the head of the list;
processing is always strictly FIFO. Therefore, the simpler singly-linked
QSIMPLEQ can be used instead.
Reviewed-by: Stefan Hajnoczi
Signed-off-by: Paolo Bonzini
From: Max Reitz
create_iovec() has a comment lamenting the lack of SIZE_T_MAX. Since
there actually is a SIZE_MAX, use it.
Two places use INT_MAX for checking the upper bound of a sector count
that is used as an argument for a blk_*() function (blk_discard() and
From: Alberto Garcia
This patch adds a new optional 'job-id' parameter to 'blockdev-backup'
and 'drive-backup', allowing the user to specify the ID of the block
job to be created.
The HMP 'drive_backup' command remains unchanged.
Signed-off-by: Alberto Garcia
If a node name instead of a BlockBackend name is specified as the driver
for a guest device, an anonymous BlockBackend is created now.
The order of operations in release_drive() must be reversed in order to
avoid a use-after-free bug because now blk_detach_dev() frees the last
reference if an
From: Alberto Garcia
The 'device' field in all BLOCK_JOB_* events and 'block-job-*' command
is no longer the device name, but the ID of the job. This patch
updates the documentation to clarify that.
Signed-off-by: Alberto Garcia
Reviewed-by: Max Reitz
From: Fam Zheng
Signed-off-by: Fam Zheng
Reviewed-by: Max Reitz
Reviewed-by: Kevin Wolf
Reviewed-by: John Snow
Signed-off-by: Kevin Wolf
---
block/raw-posix.c | 10 +-
1 file
From: Alberto Garcia
This patch adds a new optional 'job-id' parameter to 'blockdev-mirror'
and 'drive-mirror', allowing the user to specify the ID of the block
job to be created.
The HMP 'drive_mirror' command remains unchanged.
Signed-off-by: Alberto Garcia
From: Fam Zheng
And use it in qemu_dup_flags.
Signed-off-by: Fam Zheng
Reviewed-by: Eric Blake
Reviewed-by: John Snow
Signed-off-by: Kevin Wolf
---
include/qemu/osdep.h | 3 +++
util/osdep.c |
From: Paolo Bonzini
The next patch moves the coroutine argument from first-enter to
creation time. In this case, coroutine has not been initialized
yet when the coroutine is created, so change to a pointer.
Signed-off-by: Paolo Bonzini
Reviewed-by:
From: Alberto Garcia
'stream-start' has a parameter called 'backing-file', which is the
string to be written to bs->backing when the job finishes.
In the stream_start() implementation it is called 'backing_file_str',
but it the prototype in the header file it is called
From: Alberto Garcia
img_commit() creates a block job without an ID. This is no longer
allowed now that we require it to be unique and well-formed. We were
solving this by having a fallback in block_job_create(), but now that
we extended the API of commit_active_start() we can
From: Alberto Garcia
When a new job is created, the job ID is taken from the device name of
the BDS. This patch adds a new 'job_id' parameter to let the caller
provide one instead.
This patch also verifies that the ID is always unique and well-formed.
This causes problems in a
From: Alberto Garcia
This patch adds a new optional 'job-id' parameter to 'block-stream',
allowing the user to specify the ID of the block job to be created.
The HMP 'block_stream' command remains unchanged.
Signed-off-by: Alberto Garcia
Reviewed-by: Kevin
The following changes since commit ca3d87d4c84032f19478010b5604cac88b045c25:
Merge remote-tracking branch 'remotes/armbru/tags/pull-include-2016-07-12'
into staging (2016-07-12 16:04:36 +0100)
are available in the git repository at:
git://repo.or.cz/qemu/kevin.git tags/for-upstream
for
From: Alberto Garcia
find_block_job() looks for a block backend with a specified name,
checks whether it has a block job and acquires its AioContext.
We want to identify jobs by their ID and not by the block backend
they're attached to, so this patch ignores the backends
From: Alberto Garcia
The 'id' field of the BlockJob structure will be able to hold any ID,
not only a device name. This patch updates the description of that
field and the error messages where it is being used.
Soon we'll add the ability to set an arbitrary ID when creating a
From: Alberto Garcia
Currently the way to look for a specific block job is to iterate the
list manually using block_job_next().
Since we want to be able to identify a job primarily by its ID it
makes sense to have a function that does just that.
Signed-off-by: Alberto Garcia
* Gerd Hoffmann (kra...@redhat.com) wrote:
> qxl_set_dirty() expects start and end as range specification.
> qxl_dirty_one_surface passes 'size' instead of 'offset + size' as end
> parameter. Fix that. Also use uint64_t everywhere while being at it.
>
> Bug was added by "e25139b qxl: set only
a. a helper function sets a flag within env
b. cpu_get_tb_cpu_state introduces this flag, though tb.flags, for code
generation by gen_intermediate_code
c. the code is generated
d. the flag remains to be set within env. Who clear it?
On Wed, Jul 13, 2016 at 3:54 AM, Michael Rolnik
On Wed, 13 Jul 2016 11:10:21 +0200
Greg Kurz wrote:
> Now that properties are set with -global, if we pass a bogus value for
> compat mode, a warning is printed and the property is simply ignored.
> For example, if the host is POWER8 and we pass compat=POWER7 instead of
>
qxl_set_dirty() expects start and end as range specification.
qxl_dirty_one_surface passes 'size' instead of 'offset + size' as end
parameter. Fix that. Also use uint64_t everywhere while being at it.
Bug was added by "e25139b qxl: set only off-screen surfaces dirty instead
of the whole vram"
Xenstore watches of the /local/domain//backend/ directories
are never removed. This can lead to a memory leak in xenstored,
especially when xenstored is running in another domain (this will be
the case either for a system with xenstore-stubdom, or with driver
domains running qemu-based backends).
Thanks for reposting this Paolo.
I tested it by applying it on top of qemu. In libguestfs sources we
have a benchmark program called utils/boot-benchmark/boot-benchmark.
Using the qemu package from Fedora (qemu-2.6.0-3.fc24.x86_64):
$ killall -STOP firefox
$ ./boot-benchmark
Result:
On 07/13/2016 01:57 AM, Roman Pen wrote:
> v1..v2:
>
> o comment tweaks.
> o fix QEMU coding style.
The above comments should be delayed...
>
> Invoking io_setup(MAX_EVENTS) we ask kernel to create ring buffer for us
> with specified number of events. But kernel ring buffer allocation
On 07/13/2016 07:40 PM, Paolo Bonzini wrote:
On 13/07/2016 13:40, Cao jin wrote:
On 07/13/2016 06:21 PM, Paolo Bonzini wrote:
On 13/07/2016 11:06, Cao jin wrote:
When passed argument 'ns' is 0, macro DIV_ROUND_UP will return 0 also.
It's potentially slower though.
Is it because
On 13.07.2016 12:00, Greg Kurz wrote:
> It is not possible to set the compat property to an unknown value with
> powerpc_set_compat(). Something must have gone terribly wrong in QEMU,
> if we detect an "Internal error" in powerpc_get_compat(). Let's abort then.
>
> This patch also drops the
Am 13.07.2016 um 13:33 hat Roman Penyaev geschrieben:
> Just to be sure that we are on the same page:
>
> 1. We have this commit "linux-aio: Cancel BH if not needed" which
>
>a) introduces performance regression on my fio workloads on the
> following config: "iothread=1, VCPU=8, MQ=8".
On 13/07/2016 13:40, Cao jin wrote:
>
>
> On 07/13/2016 06:21 PM, Paolo Bonzini wrote:
>>
>>
>> On 13/07/2016 11:06, Cao jin wrote:
>>> When passed argument 'ns' is 0, macro DIV_ROUND_UP will return 0 also.
>>
>> It's potentially slower though.
>>
>
> Is it because the function in the i/o
On 13/07/2016 13:29, Markus Armbruster wrote:
>> > I'm curious about one thing. Eric/Markus, it would be nice to open code
>> > the visit of the list with
>> >
>> > visit_start_list(v, name, NULL, 0, );
>> > if (err) {
>> > goto out;
>> > }
>> > ...
>> >
If a node name instead of a BlockBackend name is specified as the driver
for a guest device, an anonymous BlockBackend is created now.
The order of operations in release_drive() must be reversed in order to
avoid a use-after-free bug because now blk_detach_dev() frees the last
reference if an
On Wed, Jul 13, 2016 at 12:31 PM, Paolo Bonzini wrote:
>
>
> On 13/07/2016 09:57, Roman Pen wrote:
>> v1..v2:
>>
>> o comment tweaks.
>> o fix QEMU coding style.
>>
>> Invoking io_setup(MAX_EVENTS) we ask kernel to create ring buffer for us
>> with specified number of
On 07/13/2016 06:21 PM, Paolo Bonzini wrote:
On 13/07/2016 11:06, Cao jin wrote:
When passed argument 'ns' is 0, macro DIV_ROUND_UP will return 0 also.
It's potentially slower though.
Is it because the function in the i/o loop path, so the potentially
extra arithmetical instructions
Paolo Bonzini writes:
> On 13/07/2016 06:18, Xiao Guangrong wrote:
>>
>> Return MAX_NODES under this case to fix this bug
>>
>> Signed-off-by: Xiao Guangrong
>> ---
>> backends/hostmem.c | 22 ++
>> 1 file changed, 14
101 - 200 of 247 matches
Mail list logo