From: Stephen Hemminger <stephen@networkplumber.org>
To: Vivien Didelot <vivien.didelot@gmail.com>
Cc: dev@dpdk.org, patrick.keroulas@radio-canada.ca, thomas@monjalon.net
Subject: Re: [dpdk-dev] [PATCH 1/2] net/pcap: support software Tx nanosecond timestamp
Date: Sat, 23 May 2020 18:39:50 -0700 [thread overview]
Message-ID: <20200523183950.562eb25d@hermes.lan> (raw)
In-Reply-To: <20200523172130.2285380-1-vivien.didelot@gmail.com>
On Sat, 23 May 2020 13:21:29 -0400
Vivien Didelot <vivien.didelot@gmail.com> wrote:
> When capturing packets into a PCAP file, DPDK currently uses
> microseconds for the timestamp. But libpcap supports interpreting
> tv_usec as nanoseconds depending on the file timestamp precision.
>
> To support this, use PCAP_TSTAMP_PRECISION_NANO when creating the
> empty PCAP file as specified by PCAP_OPEN_DEAD(3PCAP) and implement
> nanosecond timeval addition. This also ensures that the precision
> reported by capinfos is nanoseconds (9).
>
> Signed-off-by: Vivien Didelot <vivien.didelot@gmail.com>
> ---
> drivers/net/pcap/rte_eth_pcap.c | 15 ++++++++++++---
> 1 file changed, 12 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/net/pcap/rte_eth_pcap.c b/drivers/net/pcap/rte_eth_pcap.c
> index b4c79d174..68588c3d7 100644
> --- a/drivers/net/pcap/rte_eth_pcap.c
> +++ b/drivers/net/pcap/rte_eth_pcap.c
> @@ -287,6 +287,8 @@ eth_null_rx(void *queue __rte_unused,
> return 0;
> }
>
> +#define NSEC_PER_SEC 1e9
> +
> static inline void
> calculate_timestamp(struct timeval *ts) {
> uint64_t cycles;
> @@ -294,8 +296,14 @@ calculate_timestamp(struct timeval *ts) {
>
> cycles = rte_get_timer_cycles() - start_cycles;
> cur_time.tv_sec = cycles / hz;
> - cur_time.tv_usec = (cycles % hz) * 1e6 / hz;
> - timeradd(&start_time, &cur_time, ts);
> + cur_time.tv_usec = (cycles % hz) * NSEC_PER_SEC / hz;
> +
> + ts->tv_sec = start_time.tv_sec + cur_time.tv_sec;
> + ts->tv_usec = start_time.tv_usec + cur_time.tv_usec;
> + if (ts->tv_usec > NSEC_PER_SEC) {
> + ts->tv_usec -= NSEC_PER_SEC;
> + ts->tv_sec += 1;
> + }
Please no floating point math in the fast path of capturing packets!
next prev parent reply other threads:[~2020-05-24 1:39 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-23 17:21 [dpdk-dev] [PATCH 1/2] net/pcap: support software Tx nanosecond timestamp Vivien Didelot
2020-05-23 17:21 ` [dpdk-dev] [PATCH 2/2] net/pcap: add TODO for writing Tx HW timestamp Vivien Didelot
2020-05-24 1:38 ` Stephen Hemminger
2020-06-03 17:31 ` Ferruh Yigit
2020-05-24 1:39 ` Stephen Hemminger [this message]
2020-06-03 17:50 ` [dpdk-dev] [PATCH 1/2] net/pcap: support software Tx nanosecond timestamp Ferruh Yigit
2020-06-03 20:11 ` Stephen Hemminger
[not found] ` <20200603162652.GB13716@t480s.localdomain>
2020-06-03 21:59 ` Stephen Hemminger
2020-06-04 10:52 ` Ferruh Yigit
2020-06-04 11:16 ` Ferruh Yigit
2020-06-04 10:55 ` Ferruh Yigit
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200523183950.562eb25d@hermes.lan \
--to=stephen@networkplumber.org \
--cc=dev@dpdk.org \
--cc=patrick.keroulas@radio-canada.ca \
--cc=thomas@monjalon.net \
--cc=vivien.didelot@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.