Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1411823
| From | David Miller <davem@davemloft.net> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH v6 0/3] skb_array: array based FIFO for skbs |
| Date | 2016-06-02 07:00 +0200 |
| Message-ID | <rFsTD-1nj-7@gated-at.bofh.it> (permalink) |
| References | <rFdUC-8wg-17@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
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.
Back to linux.kernel | Previous | Next — Previous in thread | Next 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