Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1442634
| From | Peter Zijlstra <peterz@infradead.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records |
| Date | 2016-07-13 18:50 +0200 |
| Message-ID | <rUvwe-5D5-37@gated-at.bofh.it> (permalink) |
| References | <rUevn-2IR-7@gated-at.bofh.it> <rUevo-2IR-41@gated-at.bofh.it> <rUsI1-3Kr-11@gated-at.bofh.it> <rUt1o-47M-9@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
On Wed, Jul 13, 2016 at 04:08:55PM +0200, Daniel Borkmann wrote: > Hi Peter, > > On 07/13/2016 03:42 PM, Peter Zijlstra wrote: > > > >Ok so the nonlinear thing was it doing _two_ copies, one the regular > >__output_copy() on raw->data and second the optional fragment thingy > >using __output_custom(). > > > >Would something like this work instead? > > > >It does the nonlinear thing and the custom copy function thing but > >allows more than 2 fragments and allows each fragment to have a custom > >copy. > > > >It doesn't look obviously more expensive; it has the one ->copy branch > >extra, but then it doesn't recompute the sizes. > > Yes, that would work as well on a quick glance with diff just a bit > bigger, but more generic this way. Do you want me to adapt this into > the first patch? Please. > One question below: > > >- u64 zero = 0; > >- if (real_size - raw_size) > >- __output_copy(handle, &zero, real_size - raw_size); > > We still need the zero padding here from above with the computed > raw->size, right? Ah, yes, we need some __output*() in order to advance the handle offset. We don't _need_ to copy the 0s, but I doubt __output_skip() is much cheaper for these 1-3 bytes worth of data; we've already touched that line anyway.
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH net-next 0/3] BPF event output helper improvements Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 00:40 +0200
[PATCH net-next 3/3] bpf: avoid stack copy and use skb ctx for event output Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 00:40 +0200
[PATCH net-next 1/3] perf, events: add non-linear data support for raw records Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 00:40 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Peter Zijlstra <peterz@infradead.org> - 2016-07-13 10:00 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 11:30 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Peter Zijlstra <peterz@infradead.org> - 2016-07-13 14:20 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 15:20 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Peter Zijlstra <peterz@infradead.org> - 2016-07-13 15:50 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 16:10 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Peter Zijlstra <peterz@infradead.org> - 2016-07-13 18:50 +0200
Re: [PATCH net-next 1/3] perf, events: add non-linear data support for raw records Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 19:00 +0200
[PATCH net-next 2/3] bpf, perf: split bpf_perf_event_output Daniel Borkmann <daniel@iogearbox.net> - 2016-07-13 00:40 +0200
csiph-web