Displaying 7 results from an estimated 7 matches for "iov_iter_npages".
2017 Sep 30
2
[PATCH net-next] vhost_net: do not stall on zerocopy depletion
...y when increasing vq->num from 256 to 1024.
With 1 and 10 flows without this patch all packets use zerocopy.
With the patch, less than 1% eschews zerocopy.
With 100 flows, even without this patch, 90+% of packets are copied.
Some zerocopy packets from vhost_net fail this test in tun.c
if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
Generating packets with up to 21 frags. I'm not sure yet why or
what the fraction of these packets is. But this in turn can
disable zcopy_used in vhost_net_tx_select_zcopy for a
larger share of packets:
return !net->tx_flush &&...
2017 Sep 30
2
[PATCH net-next] vhost_net: do not stall on zerocopy depletion
...y when increasing vq->num from 256 to 1024.
With 1 and 10 flows without this patch all packets use zerocopy.
With the patch, less than 1% eschews zerocopy.
With 100 flows, even without this patch, 90+% of packets are copied.
Some zerocopy packets from vhost_net fail this test in tun.c
if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
Generating packets with up to 21 frags. I'm not sure yet why or
what the fraction of these packets is. But this in turn can
disable zcopy_used in vhost_net_tx_select_zcopy for a
larger share of packets:
return !net->tx_flush &&...
2023 Sep 04
0
[PATCH net-next v7 4/4] vsock/virtio: MSG_ZEROCOPY flag support
...re
>zerocopy will fallback to copy!
>
>I'll fix it and add new test!
yep, I agree!
>
>>
>> Can we also mention in the commit description why this is need only for
>> virtio_tranport and not for vhost and loopback?
>>
>>> +??????? int pages_in_iov = iov_iter_npages(iov_iter, MAX_SKB_FRAGS);
>>> +??????? int pages_to_send = min(pages_in_iov, MAX_SKB_FRAGS);
>>> +
>>> +??????? return t_ops->can_msgzerocopy(pages_to_send);
>>> +??? }
>>> +
>>> +??? return true;
>>> +}
>>> +
[...]
>&g...
2017 Sep 28
9
[PATCH net-next] vhost_net: do not stall on zerocopy depletion
From: Willem de Bruijn <willemb at google.com>
Vhost-net has a hard limit on the number of zerocopy skbs in flight.
When reached, transmission stalls. Stalls cause latency, as well as
head-of-line blocking of other flows that do not use zerocopy.
Instead of stalling, revert to copy-based transmission.
Tested by sending two udp flows from guest to host, one with payload
of
2017 Sep 28
9
[PATCH net-next] vhost_net: do not stall on zerocopy depletion
From: Willem de Bruijn <willemb at google.com>
Vhost-net has a hard limit on the number of zerocopy skbs in flight.
When reached, transmission stalls. Stalls cause latency, as well as
head-of-line blocking of other flows that do not use zerocopy.
Instead of stalling, revert to copy-based transmission.
Tested by sending two udp flows from guest to host, one with payload
of
2019 Jul 24
20
[PATCH 00/12] block/bio, fs: convert put_page() to put_user_page*()
From: John Hubbard <jhubbard at nvidia.com>
Hi,
This is mostly Jerome's work, converting the block/bio and related areas
to call put_user_page*() instead of put_page(). Because I've changed
Jerome's patches, in some cases significantly, I'd like to get his
feedback before we actually leave him listed as the author (he might
want to disown some or all of these).
I added a
2019 Jul 24
20
[PATCH 00/12] block/bio, fs: convert put_page() to put_user_page*()
From: John Hubbard <jhubbard at nvidia.com>
Hi,
This is mostly Jerome's work, converting the block/bio and related areas
to call put_user_page*() instead of put_page(). Because I've changed
Jerome's patches, in some cases significantly, I'd like to get his
feedback before we actually leave him listed as the author (he might
want to disown some or all of these).
I added a