Cake - FQ_codel the next generation
 help / color / mirror / Atom feed
From: Dave Taht <dave.taht@gmail.com>
To: cake@lists.bufferbloat.net
Subject: [Cake] cake xstats structure borken
Date: Sun, 22 Nov 2015 21:01:10 +0100	[thread overview]
Message-ID: <CAA93jw4u0YNkKGoRfCakCBk=WJ0ONsE1j80QA7pn7cUvsQtN9w@mail.gmail.com> (raw)

A) We should switch to a TCA_CAKE_XSTATS (losing things like ldelay
and breaking the ABI)
B) I don' think this stuff ever worked, (?) which means breaking the
ABI doesn't matter.

static int cake_print_xstats(struct qdisc_util *qu, FILE *f,
                                 struct rtattr *xstats)
{
        /* fq_codel stats format borrowed */
        struct tc_fq_codel_xstats *st;
        struct tc_cake_xstats     *stnc;
        SPRINT_BUF(b1);
        SPRINT_BUF(b2);
...

       if (st->type == TCA_FQ_CODEL_XSTATS_QDISC &&
RTA_PAYLOAD(xstats) >= sizeof(*st)) {
                fprintf(f, "  maxpacket %u drop_overlimit %u
new_flow_count %u ecn_mark %u",
                        st->qdisc_stats.maxpacket,
                        st->qdisc_stats.drop_overlimit,
                        st->qdisc_stats.new_flow_count,
                        st->qdisc_stats.ecn_mark); // DT> ??
                fprintf(f, "\n  new_flows_len %u old_flows_len %u",
                        st->qdisc_stats.new_flows_len,
                        st->qdisc_stats.old_flows_len);
        } else if (st->type == TCA_FQ_CODEL_XSTATS_CLASS &&
RTA_PAYLOAD(xstats) >= sizeof(*st)) {
                fprintf(f, "  deficit %d count %u lastcount %u ldelay %s",
                        st->class_stats.deficit,
                        st->class_stats.count,
                        st->class_stats.lastcount, // DT> ??
                        sprint_time(st->class_stats.ldelay, b1));
                if (st->class_stats.dropping) {
                        fprintf(f, " dropping");


qdisc fq_codel 8033: root refcnt 2 limit 10240p flows 1024 quantum
1514 target 5.0ms interval 100.0ms ecn
 Sent 1538 bytes 21 pkt (dropped 0, overlimits 0 requeues 0)
 backlog 0b 0p requeues 0

DT> What is missing is the equivalent to fq_codel's

  maxpacket 0 drop_overlimit 0 new_flow_count 0 ecn_mark 0
  new_flows_len 0 old_flows_len 0

DT> Which you can also see MIA in:

 tc -s class show dev enp3s0

class fq_codel 8035:3f9 parent 8035:
 (dropped 0, overlimits 0 requeues 0)
 backlog 1514b 0p requeues 0
  deficit 1374 count 0 lastcount 0 ldelay 4.3ms
class fq_codel 8035:3fb parent 8035:
 (dropped 0, overlimits 0 requeues 0)
 backlog 1514b 0p requeues 0
  deficit 1374 count 0 lastcount 0 ldelay 4.7ms





Dave Täht
Let's go make home routers and wifi faster! With better software!
https://www.gofundme.com/savewifi

                 reply	other threads:[~2015-11-22 20:01 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

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

  List information: https://lists.bufferbloat.net/postorius/lists/cake.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAA93jw4u0YNkKGoRfCakCBk=WJ0ONsE1j80QA7pn7cUvsQtN9w@mail.gmail.com' \
    --to=dave.taht@gmail.com \
    --cc=cake@lists.bufferbloat.net \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox