On 07/19/2018 07:15 AM, guangrong.xiao@xxxxxxxxx wrote:
From: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxx> Instead of putting the main thread to sleep state to wait for free compression thread, we can directly post it out as normal page that reduces the latency and uses CPUs more efficiently A parameter, compress-wait-thread, is introduced, it can be enabled if the user really wants the old behavior Signed-off-by: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxx> --- hmp.c | 8 ++++++++ migration/migration.c | 21 +++++++++++++++++++++ migration/migration.h | 1 + migration/ram.c | 45 ++++++++++++++++++++++++++------------------- qapi/migration.json | 23 ++++++++++++++++++----- 5 files changed, 74 insertions(+), 24 deletions(-)
+++ b/qapi/migration.json @@ -462,6 +462,11 @@ # @compress-threads: Set compression thread count to be used in live migration, # the compression thread count is an integer between 1 and 255. # +# @compress-wait-thread: Wait if no thread is free to compress the memory page +# if it's enabled, otherwise, the page will be posted out immediately +# in the main thread without compression. It's off on default. +# (Since: 3.0)
Is this a bug fix? It's awfully late in the release cycle to be adding new features; is this something that we can live without until 3.1?
-- Eric Blake, Principal Software Engineer Red Hat, Inc. +1-919-301-3266 Virtualization: qemu.org | libvirt.org
