Hi all,
I met the following issue in my expeirment of vm live storage migration.
I install the libvirt-bin and qemu in the ubuntu system.
I directly install them through the following commands.
sudo apt-get install libvirt-bin, kvm
After this isntallation, everything works well.
Now, when I
Thank you Stefan! Now I understand the workflow.
-Yaodong
On Fri, Jan 30, 2015 at 2:37 PM, Stefan Hajnoczi wrote:
> On Fri, Jan 30, 2015 at 8:13 PM, Yaodong Yang
> wrote:
> > An follow up questions.
> >
> > Suppose I have a running VM with two virtual disks, I would l
case, "migrate -b" has a higher VM downtime
during the migration.
Yaodong
On Fri, Jan 30, 2015 at 1:21 PM, Eric Blake wrote:
> On 01/30/2015 09:25 AM, Yaodong Yang wrote:
> > Hi all,
> >
> > I'm investigating the current schemes for the VM live storage m
Hi all,
I'm investigating the current schemes for the VM live storage migration in
QEMU system. I have the following questions:
1. What is the functionality of drive_mirror in QEMU? Is it designed as a
VM live storage migration approach?
2. What's the difference between drive_mirror and vMotion?
Hi community,I have a quick question about the virtio inside qemu. When the user application sends to a specific virtual disk a large number of read requests in a very short time, where should these requests be queued? Inside the virtqueue? virtqueue available ring or the underlying bdrv_read_aio()
Inside file ./hw/virtio/virtio.c, The following structs are defined. I understood that for each virtual disk, there is a corresponding queue and this queue is implemented by a ring. My questions is what is the meaning of each element inside struct VRing?Thanks a lot!typedef struct VRing{ unsigne
Hi all,At any given time, how do we get the number of IO requests for a certain disk in the virtqueue? These requests are waiting for the process.Thanks!Yaodong
Hi all,How to get the number of io requests inside the virtio queue, from a linux guest vm to a given virtual disk, in a given time?Thanks!
Hi everyone,I know that inside the qemu monitor, we can set the max migration speed through " set_migration_speed 32 ". This '32' means 32MB.My confusion is about the meaning of this 32MB. I checked the code and find that this '32MB' is the buffer size insde QemuFile, which include all the data sub
Hi all,
Does the Qemu have the storage migration tool, like the io-mirroring inside the
vmware? io-mirroring means for all the ioes, they are send to both source and
destination at the same time.
Thanks!
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?
Thanks!
Hi all,
I read the slides "An Update Overview of the QEMU Storage Stack", which
indicate that if caching mode=none, the host page cache is off and guest disk
write cache is on. My question is where the implementation is inside the qemu.
How to control the io to a virtual disk image( a raw disk
Hi all,In block-migration.c file, line 435, if (bdrv_get_dirty(bmds->bs, sector)) {It looks like this "if statement" is used to check whether a chunk is dirty or not. If it is dirty, system will migrate a whole chunk, 1MB data, to the destination. Otherwise, the cur_dirty will increase by 1MB/512B
Hi all,
I'm wondering is there any io queue inside qemu? Is there any IO scheduling
inside it? I notice that there is an IO track feature inside block.c, but I do
not know the purpose of it. Could someone explain it for me? Thanks a lot!
Yaodong
Hi all,
1. I create a raw image named as win8.img, using the following command:
/usr/local/kvm/bin/qemu-img create -f raw win8.img 20G
2. I try to install win8 with the following command, but I failed several times.
sudo /usr/local/kvm/bin/qemu-system-x86_64 -enable-kvm -drive
file=./win8.img,i
Hi all,Inside qemu, there is block-migration feature, like migrate -b. There is also a migrate_set_speed feature inside the monitor to control the migration thread. I am wondering can we make some setting to let migration thread yield to Io thread, or let the migration thread has the higher priorit
When a new work thread, which is not inside coroutine, enter a coroutine(named as A), what happened to the work thread? Is it true that the work thread also become a coroutine, or it just stop? Later if the coroutine A call yield. what happened to the work thread?
coroutine, bottom-half schemes are used for the
migration job. is there any reference material related?
Thanks a lot !
Yaodong
it send s the bdrv_co_do_readv(block.c) function is exectued
On Aug 27, 2013, at 2:45 AM, Stefan Hajnoczi wrote:
> On Mon, Aug 26, 2013 at 09:59:51PM
In the block-migration period, each chunk of data is read by bdrv_aio_readv(),
then bdrv_co_aio_rw_vector() , then bdrv_co_do_rw().
Inside the bdrv_co_do_rw() function, the bdrv_co_do_readv() function is called
twice. and exit without finish the execution of the bdrv_co_do_readv()
function. Al
I'm a newer in QEMU, and I have the following questions:
1. Is it true that all the requests to disk images need to go through function
bdrv_co_do_readv() or bdrv_co_do_writev()?
2. In block-migration thread, the bdrv_co_do_readv is also called to read
blocks from disk images, in order to finis
Hello Laszlo,
Thank you very much for your very informative answer! It makes me understood
totally about the bitmap calculation.
Thanks again!
Yaodong
On Aug 16, 2013, at 9:45 AM, Laszlo Ersek wrote:
> On 08/16/13 15:39, Yaodong Yang wrote:
>> Hello everyone,
>>
>>
Hello everyone,in QEMU 1.5.1, block-migration.c, there is a function below:static void alloc_aio_bitmap(BlkMigDevState *bmds){ BlockDriverState *bs = bmds->bs; int64_t bitmap_size; bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS) + BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
It works! Thank you very much!
Best,
Yaodong
--
Yaodong Yang
Ph.D. Student
Department of Computer Science & Engineering
University of Nebraska-Lincoln
Email: yaodong.ya...@gmail.com OR yy...@cse.unl.edu
On Aug 9, 2013, at 12:25 PM, Max Fili
Hello Peter,
Best,
Yaodong
--
Yaodong Yang
Ph.D. Student
Department of Computer Science & Engineering
University of Nebraska-Lincoln
Email: yaodong.ya...@gmail.com OR yy...@cse.unl.edu
On Aug 9, 2013, at 11:56 AM, Peter Maydell wrote:
&g
Hello everyone,
I have a simple question about the debugging of qemu.
I used the qemu-1.5.1, and added several .c and .h files related the block
drivers. I want to debug my own implementations using gdb. but I have no
idea how to do it.
I tried the following commands.
./configure --enable-debug
Hi everyone,
Previously, I used the qemu-kvm-1.2.0 from
(http://www.linux-kvm.org/page/Downloads), and it worked well in my ubuntu
server. Later, I found that some of the implementation(qemu-kvm-1.2.0) is out
of date, so that I changed to qemu-1.5.1 (http://wiki.qemu.org/Download). I
found tha
hello everyone,
I have a question about the qemu block-subsytem. When a user in guest os
perform an io operation, how this io request performed in the qemu. Where
is the start point in qemu code to serve this request.
Thanks!
--
Yaodong Yang
Computer Science and Engineering Department
Yes, I found it in the qemu-1.5.1 and it's much clear for me now. I think I
need to work on this version, other than the out-of-date version
qemu-kvm-1.2.0. Thanks a lot.
On Mon, Jul 8, 2013 at 12:29 PM, Yaodong Yang wrote:
> I used the qemu-kvm 1.2.0, so I did not find it in the code
I used the qemu-kvm 1.2.0, so I did not find it in the code. I will move to
the current qemu version. Thanks!
On Mon, Jul 8, 2013 at 12:18 PM, Michael Roth wrote:
> Quoting Yaodong Yang (2013-07-08 10:57:25)
> > Hello Michael,
> >Thanks for your help!
> >I
n loop. Is it correct?
Also, I did not find any thread_create related function in the
migrate_fd_connect() function.
I think my current goal is to find the exact start point of the migration
thread. Thanks again.
Yaodong
On Mon, Jul 8, 2013 at 10:32 AM, Michael Roth wrote:
> Quoting Yaodo
main loop (main_loop_wait(int
nonblocking) function). I want to know is there a new dedicated thread
created for this migration task or not? If so, where in the code the new
thread created.
Thanks!
Yaodong
--
Yaodong Yang
Computer Science and Engineering Department
University of Nebraska--Lincoln,
L
Hi all,
I'm a newer in QEMU-KVM. When I read the source code of qemu-kvm-1.2.0, I can
not find the definition of some types, like RunState (in Vl.c file). I also
checked the kvm-kmod-3.5, but I still can not find the definition. Could anyone
give me some hints about where to find it. Thanks in
Best,
Yaodong
--
Yaodong Yang
Ph.D. Student
Department of Computer Science & Engineering
University of Nebraska-Lincoln
Email: yaodong.ya...@gmail.com OR yy...@cse.unl.edu
current block migration
algorithm (qemu-kvm 1.2.0).
Any information or guidance are much more appreciated! Thanks!
Best,
Yaodong
--
Yaodong Yang
Ph.D. Student
Department of Computer Science & Engineering
University of Nebraska-Lincoln
Email: yaodon
34 matches
Mail list logo
