[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [virtio-dev] Re: [PATCH v7 kernel 3/5] virtio-balloon:
From: |
David Hildenbrand |
Subject: |
Re: [Qemu-devel] [virtio-dev] Re: [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER |
Date: |
Fri, 10 Mar 2017 14:26:18 +0100 |
User-agent: |
Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.7.0 |
Am 10.03.2017 um 11:02 schrieb Wei Wang:
> On 03/08/2017 12:01 PM, Michael S. Tsirkin wrote:
>> On Fri, Mar 03, 2017 at 01:40:28PM +0800, Wei Wang wrote:
>>> From: Liang Li <address@hidden>
>>>
>>> The implementation of the current virtio-balloon is not very
>>> efficient, because the pages are transferred to the host one by one.
>>> Here is the breakdown of the time in percentage spent on each
>>> step of the balloon inflating process (inflating 7GB of an 8GB
>>> idle guest).
>>>
>>> 1) allocating pages (6.5%)
>>> 2) sending PFNs to host (68.3%)
>>> 3) address translation (6.1%)
>>> 4) madvise (19%)
>>>
>>> It takes about 4126ms for the inflating process to complete.
>>> The above profiling shows that the bottlenecks are stage 2)
>>> and stage 4).
>>>
>>> This patch optimizes step 2) by transfering pages to the host in
>>> chunks. A chunk consists of guest physically continuous pages, and
>>> it is offered to the host via a base PFN (i.e. the start PFN of
>>> those physically continuous pages) and the size (i.e. the total
>>> number of the pages). A normal chunk is formated as below:
>>> -----------------------------------------------
>>> | Base (52 bit) | Size (12 bit)|
>>> -----------------------------------------------
>>> For large size chunks, an extended chunk format is used:
>>> -----------------------------------------------
>>> | Base (64 bit) |
>>> -----------------------------------------------
>>> -----------------------------------------------
>>> | Size (64 bit) |
>>> -----------------------------------------------
>>>
>>> By doing so, step 4) can also be optimized by doing address
>>> translation and madvise() in chunks rather than page by page.
>>>
>>> This optimization requires the negotation of a new feature bit,
>>> VIRTIO_BALLOON_F_CHUNK_TRANSFER.
>>>
>>> With this new feature, the above ballooning process takes ~590ms
>>> resulting in an improvement of ~85%.
>>>
>>> TODO: optimize stage 1) by allocating/freeing a chunk of pages
>>> instead of a single page each time.
>>>
>>> Signed-off-by: Liang Li <address@hidden>
>>> Signed-off-by: Wei Wang <address@hidden>
>>> Suggested-by: Michael S. Tsirkin <address@hidden>
>>> Cc: Michael S. Tsirkin <address@hidden>
>>> Cc: Paolo Bonzini <address@hidden>
>>> Cc: Cornelia Huck <address@hidden>
>>> Cc: Amit Shah <address@hidden>
>>> Cc: Dave Hansen <address@hidden>
>>> Cc: Andrea Arcangeli <address@hidden>
>>> Cc: David Hildenbrand <address@hidden>
>>> Cc: Liang Li <address@hidden>
>>> Cc: Wei Wang <address@hidden>
>> Does this pass sparse? I see some endian-ness issues here.
>
> "pass sparse"- what does that mean?
> I didn't see any complaints from "make" on my machine.
https://kernel.org/doc/html/latest/dev-tools/sparse.html
Static code analysis. You have to run it explicitly.
--
Thanks,
David
- [Qemu-devel] [PATCH v7 kernel 0/5] Extend virtio-balloon for fast (de)inflating & fast live migration, Wei Wang, 2017/03/03
- [Qemu-devel] [PATCH v7 kernel 2/5] virtio-balloon: VIRTIO_BALLOON_F_CHUNK_TRANSFER, Wei Wang, 2017/03/03
- [Qemu-devel] [PATCH v7 kernel 1/5] virtio-balloon: rework deflate to add page to a list, Wei Wang, 2017/03/03
- [Qemu-devel] [PATCH v7 kernel 4/5] virtio-balloon: define flags and head for host request vq, Wei Wang, 2017/03/03
- [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Wei Wang, 2017/03/03
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Matthew Wilcox, 2017/03/09
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Wei Wang, 2017/03/10
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Michael S. Tsirkin, 2017/03/10
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Matthew Wilcox, 2017/03/10
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Michael S. Tsirkin, 2017/03/10
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Matthew Wilcox, 2017/03/10
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Michael S. Tsirkin, 2017/03/10
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Matthew Wilcox, 2017/03/10
- Re: [Qemu-devel] [PATCH v7 kernel 3/5] virtio-balloon: implementation of VIRTIO_BALLOON_F_CHUNK_TRANSFER, Michael S. Tsirkin, 2017/03/11