On 10/31/2014 06:40 AM, Liliang wrote: > From: Li Liang <liang.z...@intel.com> > > Give some details about how to use the multiple compress threads feature > in live migration. > > Signed-off-by: Li Liang <liang.z...@intel.com> > --- > docs/multiple-compression-threads.txt | 57 > +++++++++++++++++++++++++++++++++++ > 1 file changed, 57 insertions(+) > create mode 100644 docs/multiple-compression-threads.txt > > diff --git a/docs/multiple-compression-threads.txt > b/docs/multiple-compression-threads.txt > new file mode 100644 > index 0000000..83e9e5b > --- /dev/null > +++ b/docs/multiple-compression-threads.txt > @@ -0,0 +1,57 @@ > +Use multiple compression(decompression) threads in live migration
Missing a copyright notice (yeah, not all files in our docs directory
are good examples, but we're starting to get better at it).
> +=================================================================
> +Instead of sending the guest memory directly, this solution will
> +compress the ram page before sending, after receiving, the data how to
> +us will be decompressed. Using compression in live migration can help
s/how to us will be/has to be/ ?
> +to reduce the data transferred about 60%, this is very useful when the
> +bandwidth is limited, and the migration time can also be reduced about
> +80% in a typical case.
What network bandwidth did you have in your tests? I suspect that the
speedups you saw may be more pronounced on low-bandwidth links, and that
you would be wise to give more details about reproducing your test
setup, since not everyone will see the same speedups.
> +
> +The process of compression will consume additional CPU cycles, and the
> +extra CPU cycles will increase the migration time. In another hand,
s/In another/On the other/
> +the amount of data transferred will reduced, this factor can reduce
> +the migration time. If the process of the compression is quickly
s/quickly/quick/
> +enough, then the total migration time can be reduced, multiple
s/multiple/and multiple/
> +compression threads can be used to accelerate the compression process.
> +
> +Compression level can be used to control the compression speed and the
> +compression ratio. High compression ratio will take more time, level 0
> +stands for no compression, level 1 stands for the best compression
> +speed,and level 9 stands for the best compression ratio. Users can
> +select a level number between 0 and 9.
> +
> +
> +When to use the multiple compression threads in live migration
> +==============================================================
> +Compression of data will consume lot of extra CPU cycles, in a system
> +with high overhead of CPU, avoid using this feature. When the network
> +bandwidth is very limited and the CPU resource is adequate, use the
> +multiple compression threads will be very helpful. If both the CPU and
> +the network bandwidth are adequate, use multiple compression threads
> +can still help to reduce the migration time.
> +
> +
> +Usage
> +======
> +1. Verify the destination QEMU version is able to support the multiple
> +compression threads migration:
> + {qemu} info_migrate_capablilites
> + {qemu} ... compress: off ...
> +
> +2. Activate compression on the souce:
> + {qemu} migrate_set_capability compress on
> +
> +3. Set the compression thread count on source:
> + {qemu} migrate_set_compress_threads 10
> +
> +4. Set the compression level on the source:
> + {qemu} migrate_set_compress_level 1
> +
> +5. Set the decompression thread count on destination:
> + {qemu} migrate_set_decompress_threads 5
> +
> +6. Start outgoing migration:
> + {qemu} migrate -d tcp:destination.host:4444
> + {qemu} info migrate
> + Capablilties: ... compress: on
s/Capablilties/Capabilities/
--
Eric Blake eblake redhat com +1-919-301-3266
Libvirt virtualization library http://libvirt.org
signature.asc
Description: OpenPGP digital signature
