[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [Qemu-devel] [PATCH 4/4] virtio-blk: introduce multiread
From: |
Peter Lieven |
Subject: |
Re: [Qemu-devel] [PATCH 4/4] virtio-blk: introduce multiread |
Date: |
Mon, 15 Dec 2014 17:02:45 +0100 |
> Am 15.12.2014 um 17:00 schrieb Kevin Wolf <address@hidden>:
>
> Am 15.12.2014 um 16:52 hat Peter Lieven geschrieben:
>> On 15.12.2014 16:43, Peter Lieven wrote:
>>> On 15.12.2014 16:01, Kevin Wolf wrote:
>>>> Am 09.12.2014 um 17:26 hat Peter Lieven geschrieben:
>>>>> this patch finally introduces multiread support to virtio-blk. While
>>>>> multiwrite support was there for a long time, read support was missing.
>>>>>
>>>>> To achieve this the patch does several things which might need further
>>>>> explanation:
>>>>>
>>>>> - the whole merge and multireq logic is moved from block.c into
>>>>> virtio-blk. This is move is a preparation for directly creating a
>>>>> coroutine out of virtio-blk.
>>>>>
>>>>> - requests are only merged if they are strictly sequential, and no
>>>>> longer sorted. This simplification decreases overhead and reduces
>>>>> latency. It will also merge some requests which were unmergable before.
>>>>>
>>>>> The old algorithm took up to 32 requests, sorted them and tried to merge
>>>>> them. The outcome was anything between 1 and 32 requests. In case of
>>>>> 32 requests there were 31 requests unnecessarily delayed.
>>>>>
>>>>> On the other hand let's imagine e.g. 16 unmergeable requests followed
>>>>> by 32 mergable requests. The latter 32 requests would have been split
>>>>> into two 16 byte requests.
>>>>>
>>>>> Last the simplified logic allows for a fast path if we have only a
>>>>> single request in the multirequest. In this case the request is sent as
>>>>> ordinary request without multireq callbacks.
>>>>>
>>>>> As a first benchmark I installed Ubuntu 14.04.1 on a local SSD. The
>>>>> number of
>>>>> merged requests is in the same order while the write latency is obviously
>>>>> decreased by several percent.
>>>>>
>>>>> cmdline:
>>>>> qemu-system-x86_64 -m 1024 -smp 2 -enable-kvm -cdrom
>>>>> ubuntu-14.04.1-server-amd64.iso \
>>>>> -drive if=virtio,file=/dev/ssd/ubuntu1404,aio=native,cache=none -monitor
>>>>> stdio
>>>>>
>>>>> Before:
>>>>> virtio0:
>>>>> rd_bytes=151056896 wr_bytes=2683947008 rd_operations=18614
>>>>> wr_operations=67979
>>>>> flush_operations=15335 wr_total_time_ns=540428034217
>>>>> rd_total_time_ns=11110520068
>>>>> flush_total_time_ns=40673685006 rd_merged=0 wr_merged=15531
>>>>>
>>>>> After:
>>>>> virtio0:
>>>>> rd_bytes=149487104 wr_bytes=2701344768 rd_operations=18148
>>>>> wr_operations=68578
>>>>> flush_operations=15368 wr_total_time_ns=437030089565
>>>>> rd_total_time_ns=9836288815
>>>>> flush_total_time_ns=40597981121 rd_merged=690 wr_merged=14615
>>>>>
>>>>> Some first numbers of improved read performance while booting:
>>>>>
>>>>> The Ubuntu 14.04.1 vServer from above:
>>>>> virtio0:
>>>>> rd_bytes=97545216 wr_bytes=119808 rd_operations=5071 wr_operations=26
>>>>> flush_operations=2 wr_total_time_ns=8847669 rd_total_time_ns=13952575478
>>>>> flush_total_time_ns=3075496 rd_merged=742 wr_merged=0
>>>>>
>>>>> Windows 2012R2 (booted from iSCSI):
>>>>> virtio0: rd_bytes=176559104 wr_bytes=61859840 rd_operations=7200
>>>>> wr_operations=360
>>>>> flush_operations=68 wr_total_time_ns=34344992718
>>>>> rd_total_time_ns=134386844669
>>>>> flush_total_time_ns=18115517 rd_merged=641 wr_merged=216
>>>>>
>>>>> Signed-off-by: Peter Lieven <address@hidden>
>>>> Looks pretty good. The only thing I'm still unsure about are possible
>>>> integer overflows in the merging logic. Maybe you can have another look
>>>> there (ideally not only the places I commented on below, but the whole
>>>> function).
>>>>
>>>>> @@ -414,14 +402,81 @@ void virtio_blk_handle_request(VirtIOBlockReq *req,
>>>>> MultiReqBuffer *mrb)
>>>>> iov_from_buf(in_iov, in_num, 0, serial, size);
>>>>> virtio_blk_req_complete(req, VIRTIO_BLK_S_OK);
>>>>> virtio_blk_free_request(req);
>>>>> - } else if (type & VIRTIO_BLK_T_OUT) {
>>>>> - qemu_iovec_init_external(&req->qiov, iov, out_num);
>>>>> - virtio_blk_handle_write(req, mrb);
>>>>> - } else if (type == VIRTIO_BLK_T_IN || type == VIRTIO_BLK_T_BARRIER) {
>>>>> - /* VIRTIO_BLK_T_IN is 0, so we can't just & it. */
>>>>> - qemu_iovec_init_external(&req->qiov, in_iov, in_num);
>>>>> - virtio_blk_handle_read(req);
>>>>> - } else {
>>>>> + break;
>>>>> + }
>>>>> + case VIRTIO_BLK_T_IN:
>>>>> + case VIRTIO_BLK_T_OUT:
>>>>> + {
>>>>> + bool is_write = type & VIRTIO_BLK_T_OUT;
>>>>> + int64_t sector_num = virtio_ldq_p(VIRTIO_DEVICE(req->dev),
>>>>> + &req->out.sector);
>>>>> + int max_transfer_length =
>>>>> blk_get_max_transfer_length(req->dev->blk);
>>>>> + int nb_sectors = 0;
>>>>> + bool merge = true;
>>>>> +
>>>>> + if (!virtio_blk_sect_range_ok(req->dev, sector_num,
>>>>> req->qiov.size)) {
>>>>> + virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
>>>>> + virtio_blk_free_request(req);
>>>>> + return;
>>>>> + }
>>>>> +
>>>>> + if (is_write) {
>>>>> + qemu_iovec_init_external(&req->qiov, iov, out_num);
>>>>> + trace_virtio_blk_handle_write(req, sector_num,
>>>>> + req->qiov.size /
>>>>> BDRV_SECTOR_SIZE);
>>>>> + } else {
>>>>> + qemu_iovec_init_external(&req->qiov, in_iov, in_num);
>>>>> + trace_virtio_blk_handle_read(req, sector_num,
>>>>> + req->qiov.size /
>>>>> BDRV_SECTOR_SIZE);
>>>>> + }
>>>>> +
>>>>> + nb_sectors = req->qiov.size / BDRV_SECTOR_SIZE;
>>>> qiov.size is controlled by the guest, and nb_sectors is only an int. Are
>>>> you sure that this can't overflow?
>>>
>>> In theory, yes. For this to happen in_iov or iov needs to contain
>>> 2TB of data on 32-bit systems. But theoretically there could
>>> also be already an overflow in qemu_iovec_init_external where
>>> multiple size_t are summed up in a size_t.
>>>
>>> There has been no overflow checking in the merge routine in
>>> the past, but if you feel better, we could add sth like this:
>>>
>>> diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
>>> index cc0076a..e9236da 100644
>>> --- a/hw/block/virtio-blk.c
>>> +++ b/hw/block/virtio-blk.c
>>> @@ -410,8 +410,8 @@ void virtio_blk_handle_request(VirtIOBlockReq *req,
>>> MultiReqBuffer *mrb)
>>> bool is_write = type & VIRTIO_BLK_T_OUT;
>>> int64_t sector_num = virtio_ldq_p(VIRTIO_DEVICE(req->dev),
>>> &req->out.sector);
>>> - int max_transfer_length =
>>> blk_get_max_transfer_length(req->dev->blk);
>>> - int nb_sectors = 0;
>>> + int64_t max_transfer_length =
>>> blk_get_max_transfer_length(req->dev->blk);
>>> + int64_t nb_sectors = 0;
>>> bool merge = true;
>>>
>>> if (!virtio_blk_sect_range_ok(req->dev, sector_num, req->qiov.size))
>>> {
>>> @@ -431,6 +431,7 @@ void virtio_blk_handle_request(VirtIOBlockReq *req,
>>> MultiReqBuffer *mrb)
>>> }
>>>
>>> nb_sectors = req->qiov.size / BDRV_SECTOR_SIZE;
>>> + max_transfer_length = MIN_NON_ZERO(max_transfer_length, INT_MAX);
>>>
>>> block_acct_start(blk_get_stats(req->dev->blk),
>>> &req->acct, req->qiov.size,
>>> @@ -443,8 +444,7 @@ void virtio_blk_handle_request(VirtIOBlockReq *req,
>>> MultiReqBuffer *mrb)
>>> }
>>>
>>> /* merge would exceed maximum transfer length of backend device */
>>> - if (max_transfer_length &&
>>> - mrb->nb_sectors + nb_sectors > max_transfer_length) {
>>> + if (nb_sectors + mrb->nb_sectors > max_transfer_length) {
>>> merge = false;
>>> }
>>
>> May also this here:
>>
>> diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
>> index cc0076a..fa647b6 100644
>> --- a/hw/block/virtio-blk.c
>> +++ b/hw/block/virtio-blk.c
>> @@ -333,6 +333,9 @@ static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
>> uint64_t nb_sectors = size >> BDRV_SECTOR_BITS;
>> uint64_t total_sectors;
>>
>> + if (nb_sectors > INT_MAX) {
>> + return false;
>> + }
>> if (sector & dev->sector_mask) {
>> return false;
>> }
>>
>>
>> Thats something that has not been checked for ages as well.
>
> Adding checks can never hurt, so go for it. ;-)
i will add both checks and Fams comment and send a v2 tomorrow.
Peter
>
> Kevin
- [Qemu-devel] [PATCH 2/4] hw/virtio-blk: add a constant for max number of merged requests, (continued)
[Qemu-devel] [PATCH 3/4] block-backend: expose bs->bl.max_transfer_length, Peter Lieven, 2014/12/09