Skip to contentSkip to conversation

net_sched: precision problem of TBF/HTB

DISCUSSION Yang Yingliang 4 participants 4 messages Jul 16, 2013 – Jul 17, 2013

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Hi, Eric
Commit 1def9238d4aa2 (net_sched: more precise pkt_len computation) makes more precise transfer bytes by taking account of headers in qdisc_skb_cb(skb)->pkt_len, but this introduces a problem with calculating bandwidth in userland.

When calculating bandwidth in userland, it's not include headers' bytes. From the user's perspective, it's not a correct bandwidth.

Shall we need take account of headers in qdisc_skb_cb(skb)->pkt_len or just skb->len?

Example:
tc qdisc add dev $DEV root handle 1: tbf latency 50ms burst 500kB rate 500mbit mtu 64k

iperf -c host -t 30 -i 10
[ ID] Interval Transfer Bandwidth

[  3]  0.0-10.0 sec   571 MBytes   479 Mbits/sec
[  3] 10.0-20.0 sec   570 MBytes   478 Mbits/sec
[  3] 20.0-30.0 sec   570 MBytes   478 Mbits/sec
[  3]  0.0-30.0 sec  1.67 GBytes   478 Mbits/sec
#1 lore raw
Quoted 6 lines · Yang Yingliang

Hi, Eric
Commit 1def9238d4aa2 (net_sched: more precise pkt_len computation) makes more precise transfer bytes by taking account of headers in qdisc_skb_cb(skb)->pkt_len, but this introduces a problem with calculating bandwidth in userland.

This changed nothing to userland.

Quoted 8 lines

When calculating bandwidth in userland, it's not include headers' bytes. From the user's perspective, it's not a correct bandwidth.

Shall we need take account of headers in qdisc_skb_cb(skb)->pkt_len or just skb->len?

These values are not accessible from userland, unless you capture packets with a sniffer (tcpdump or something like that)

Quoted 10 lines

Example:
tc qdisc add dev $DEV root handle 1: tbf latency 50ms burst 500kB rate 500mbit mtu 64k

iperf -c host -t 30 -i 10
[ ID] Interval Transfer Bandwidth

[  3]  0.0-10.0 sec   571 MBytes   479 Mbits/sec
[  3] 10.0-20.0 sec   570 MBytes   478 Mbits/sec
[  3] 20.0-30.0 sec   570 MBytes   478 Mbits/sec
[  3]  0.0-30.0 sec  1.67 GBytes   478 Mbits/sec

iperf only measures the amount of payload, and probably do not care of headers.

You cannot accurately measure bandwidth from userland, unless making assumptions (or getting them from the stack) on header sizes (IP + TCP), MSS value, and retransmits.

#2 lore raw
Quoted 32 lines · Eric Dumazet
Quoted 6 lines · Yang Yingliang

Hi, Eric
Commit 1def9238d4aa2 (net_sched: more precise pkt_len computation) makes more precise transfer bytes by taking account of headers in qdisc_skb_cb(skb)->pkt_len, but this introduces a problem with calculating bandwidth in userland.

This changed nothing to userland.

Quoted 8 lines

When calculating bandwidth in userland, it's not include headers' bytes. From the user's perspective, it's not a correct bandwidth.

Shall we need take account of headers in qdisc_skb_cb(skb)->pkt_len or just skb->len?

These values are not accessible from userland, unless you capture packets with a sniffer (tcpdump or something like that)

Quoted 10 lines

Example:
tc qdisc add dev $DEV root handle 1: tbf latency 50ms burst 500kB rate 500mbit mtu 64k

iperf -c host -t 30 -i 10
[ ID] Interval Transfer Bandwidth

[  3]  0.0-10.0 sec   571 MBytes   479 Mbits/sec
[  3] 10.0-20.0 sec   570 MBytes   478 Mbits/sec
[  3] 20.0-30.0 sec   570 MBytes   478 Mbits/sec
[  3]  0.0-30.0 sec  1.67 GBytes   478 Mbits/sec
Quoted 8 lines

iperf only measures the amount of payload, and probably do not care of headers.

You cannot accurately measure bandwidth from userland, unless making assumptions (or getting them from the stack) on header sizes (IP + TCP), MSS value, and retransmits.

ok, for the further, can you give me some advise for how calculate the bandwidth for net link. for example,what kind of tools is better.

Quoted 7 lines

--
To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

#3 lore raw
Quoted 36 lines · Ding Tianhong
Quoted 35 lines · Eric Dumazet
Quoted 6 lines · Yang Yingliang

Hi, Eric
Commit 1def9238d4aa2 (net_sched: more precise pkt_len computation) makes more precise transfer bytes by taking account of headers in qdisc_skb_cb(skb)->pkt_len, but this introduces a problem with calculating bandwidth in userland.

This changed nothing to userland.

Quoted 8 lines

When calculating bandwidth in userland, it's not include headers' bytes. From the user's perspective, it's not a correct bandwidth.

Shall we need take account of headers in qdisc_skb_cb(skb)->pkt_len or just skb->len?

These values are not accessible from userland, unless you capture packets with a sniffer (tcpdump or something like that)

Quoted 10 lines

Example:
tc qdisc add dev $DEV root handle 1: tbf latency 50ms burst 500kB rate 500mbit mtu 64k

iperf -c host -t 30 -i 10
[ ID] Interval Transfer Bandwidth

[  3]  0.0-10.0 sec   571 MBytes   479 Mbits/sec
[  3] 10.0-20.0 sec   570 MBytes   478 Mbits/sec
[  3] 20.0-30.0 sec   570 MBytes   478 Mbits/sec
[  3]  0.0-30.0 sec  1.67 GBytes   478 Mbits/sec

iperf only measures the amount of payload, and probably do not care of headers.

Quoted 10 lines
Quoted 5 lines

You cannot accurately measure bandwidth from userland, unless making assumptions (or getting them from the stack) on header sizes (IP + TCP), MSS value, and retransmits.

ok, for the further, can you give me some advise for how calculate the bandwidth for net link. for example,what kind of tools is better.

Quoted 1 line

Vendor specific but it looks reasonably common to count tx and rx bytes in ethtool stats. Take a few samples with 'ethtool -S' and do the math. This will give you what the driver/hardware actually xmits and receives.

.John

Signature · 1 line
John Fastabend         Intel Corporation