Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1411988
| From | Jason Wang <jasowang@redhat.com> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH v6 0/3] skb_array: array based FIFO for skbs |
| Date | 2016-06-02 10:20 +0200 |
| Message-ID | <rFw1c-3rP-17@gated-at.bofh.it> (permalink) |
| References | <rFdUC-8wg-17@gated-at.bofh.it> <rFsTD-1nj-7@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On 2016年06月02日 12:51, David Miller wrote: > From: "Michael S. Tsirkin" <mst@redhat.com> > Date: Wed, 1 Jun 2016 15:54:34 +0300 > >> This is in response to the proposal by Jason to make tun >> rx packet queue lockless using a circular buffer. >> My testing seems to show that at least for the common usecase >> in networking, which isn't lockless, circular buffer >> with indices does not perform that well, because >> each index access causes a cache line to bounce between >> CPUs, and index access causes stalls due to the dependency. >> >> By comparison, an array of pointers where NULL means invalid >> and !NULL means valid, can be updated without messing up barriers >> at all and does not have this issue. >> >> On the flip side, cache pressure may be caused by using large queues. >> tun has a queue of 1000 entries by default and that's 8K. >> At this point I'm not sure this can be solved efficiently. >> The correct solution might be sizing the queues appropriately. >> >> Here's an implementation of this idea: it can be used more >> or less whenever sk_buff_head can be used, except you need >> to know the queue size in advance. > ... > > I have no fundamental issues with this piece of infrastructure, but when > it gets included I want this series to include at least one use case. > > This can be an adaptation of Jason's tun rx packet queue changes, or > similar. > > Thanks. Right, I'm working on using skb array for tun, will post the patch in the following days. Thanks
Back to linux.kernel | Previous | Next — Previous in thread | Find similar | Unroll thread
[PATCH v6 0/3] skb_array: array based FIFO for skbs "Michael S. Tsirkin" <mst@redhat.com> - 2016-06-01 15:00 +0200
[PATCH v6 2/3] ptr_ring: ring test "Michael S. Tsirkin" <mst@redhat.com> - 2016-06-01 15:00 +0200
[PATCH v6 3/3] skb_array: array based FIFO for skbs "Michael S. Tsirkin" <mst@redhat.com> - 2016-06-01 15:00 +0200
Re: [PATCH v6 3/3] skb_array: array based FIFO for skbs Jason Wang <jasowang@redhat.com> - 2016-06-02 10:20 +0200
Re: [PATCH v6 3/3] skb_array: array based FIFO for skbs "Michael S. Tsirkin" <mst@redhat.com> - 2016-06-02 11:30 +0200
[PATCH v6 1/3] ptr_ring: array based FIFO for pointers "Michael S. Tsirkin" <mst@redhat.com> - 2016-06-01 15:00 +0200
Re: [PATCH v6 0/3] skb_array: array based FIFO for skbs David Miller <davem@davemloft.net> - 2016-06-02 07:00 +0200
Re: [PATCH v6 0/3] skb_array: array based FIFO for skbs Jason Wang <jasowang@redhat.com> - 2016-06-02 10:20 +0200
csiph-web