Searched hist:dcaf446e (Results 1 – 3 of 3) sorted by relevance
/qemu/migration/ |
H A D | qemu-file.h | dcaf446e Fri Mar 30 07:51:20 GMT 2018 Xiao Guangrong <xiaoguangrong@tencent.com> migration: stop compression to allocate and free memory frequently
Current code uses compress2() to compress memory which manages memory internally, that causes huge memory is allocated and freed very frequently
More worse, frequently returning memory to kernel will flush TLBs and trigger invalidation callbacks on mmu-notification which interacts with KVM MMU, that dramatically reduce the performance of VM
So, we maintain the memory by ourselves and reuse it for each compression
Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn> Signed-off-by: Xiao Guangrong <xiaoguangrong@tencent.com> Message-Id: <20180330075128.26919-3-xiaoguangrong@tencent.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
|
H A D | qemu-file.c | dcaf446e Fri Mar 30 07:51:20 GMT 2018 Xiao Guangrong <xiaoguangrong@tencent.com> migration: stop compression to allocate and free memory frequently
Current code uses compress2() to compress memory which manages memory internally, that causes huge memory is allocated and freed very frequently
More worse, frequently returning memory to kernel will flush TLBs and trigger invalidation callbacks on mmu-notification which interacts with KVM MMU, that dramatically reduce the performance of VM
So, we maintain the memory by ourselves and reuse it for each compression
Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn> Signed-off-by: Xiao Guangrong <xiaoguangrong@tencent.com> Message-Id: <20180330075128.26919-3-xiaoguangrong@tencent.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
|
H A D | ram.c | dcaf446e Fri Mar 30 07:51:20 GMT 2018 Xiao Guangrong <xiaoguangrong@tencent.com> migration: stop compression to allocate and free memory frequently
Current code uses compress2() to compress memory which manages memory internally, that causes huge memory is allocated and freed very frequently
More worse, frequently returning memory to kernel will flush TLBs and trigger invalidation callbacks on mmu-notification which interacts with KVM MMU, that dramatically reduce the performance of VM
So, we maintain the memory by ourselves and reuse it for each compression
Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn> Signed-off-by: Xiao Guangrong <xiaoguangrong@tencent.com> Message-Id: <20180330075128.26919-3-xiaoguangrong@tencent.com> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
|