There are the outputs : vpp# show buffer traces
Pool Name Index NUMA Size Data Size Total Avail Cached
Used
default-numa-0 0 0 2496 2048 17640 0 152
17488
Node Allocated Freed
In Out Buffered
api-rx-from-ring 1 0
0 0 1
GigabitEthernetb/0/0-tx 0 0
11 0 11
unix-cli-local:4 10 0
0 0 10
dpdk-input 36221 34867
0 56450605 -56449251
GigabitEthernetb/0/0-tx 0 0
8 0 8
GigabitEthernet13/0/0-tx 0 0
56449411 0 56449411
dpdk-input 0 0
0 93 -93
vpp# show buffer traces verbose
Pool Name Index NUMA Size Data Size Total Avail Cached
Used
default-numa-0 0 0 2496 2048 17640 0 168
17472
Node Allocated Freed
In Out Buffered
api-rx-from-ring 1 0
0 0 1
ip4-glean 10 0
10 20 0
ip4-drop 0 0
10 10 0
ip4-lookup 0 0
10 10 0
error-drop 0 0
10 10 0
drop 0 10
10 0 0
GigabitEthernetb/0/0-tx 0 0
11 0 11
GigabitEthernetb/0/0-output 0 0
11 11 0
unix-cli-local:4 10 0
0 0 10
gtpu4-input 0 0
56450054 56450054 0
dpdk-input 36221 34867
0 56450605 -56449251
arp-reply 0 0
390 390 0
arp-input 0 0
390 390 0
ip4-mfib-forward-rpf 0 0
9 9 0
ip4-mfib-forward-lookup 0 0
9 9 0
ip4-udp-lookup 0 0
56450054 56450054 0
ip4-glean 9 0
652 661 0
ip6-input 0 0
98 98 0
ip6-not-enabled 0 0
98 98 0
ip4-input 0 0
112900143 112900143 0
ip4-drop 0 0
687 687 0
ip4-rewrite 0 0
56449402 56449402 0
ip4-local 0 0
56450054 56450054 0
ip4-lookup 0 0
112900134 112900134 0
ethernet-input 0 0
56450605 56450605 0
ip4-policer-classify 0 0
56450054 56450054 0
interface-output 0 0
8 8 0
error-punt 0 0
28 28 0
error-drop 0 0
1167 1167 0
punt 0 28
28 0 0
drop 0 1167
1167 0 0
GigabitEthernetb/0/0-tx 0 0
8 0 8
GigabitEthernetb/0/0-output 0 0
8 8 0
GigabitEthernet13/0/0-tx 0 0
56449411 0 56449411
GigabitEthernet13/0/0-output 0 0
56449411 56449411 0
dpdk-input 0 0
0 109 -109
ip4-mfib-forward-rpf 0 0
4 4 0
ip4-mfib-forward-lookup 0 0
4 4 0
ip6-input 0 0
101 101 0
ip6-not-enabled 0 0
101 101 0
ip4-options 0 0
4 4 0
ip4-input 0 0
8 8 0
ip4-drop 0 0
8 8 0
ip4-local 0 0
4 4 0
ethernet-input 0 0
109 109 0
error-drop 0 0
109 109 0
drop 0 109
109 0 0
Please help us on this mates. We were using an older version of VPP and
couldn't get these results ASAP, bganne/ole.
(PS: I would rate 3/10 myself, OLE :-D)
On Mon, Oct 11, 2021 at 12:57 PM Benoit Ganne (bganne) <[email protected]>
wrote:
> VPP uses its own buffer allocator under the hood, you should monitor the
> output of 'show buffers' instead.
> If you still see buffer leaks, you can turn on buffer tracing with 'set
> buffer traces' and share the output of 'show buffer traces'.
>
> Best
> ben
>
> > -----Original Message-----
> > From: [email protected] <[email protected]> On Behalf Of Akash S R
> > Sent: lundi 11 octobre 2021 08:27
> > To: vpp-dev <[email protected]>
> > Subject: [vpp-dev] show dpdk buffers are fully allocated slowly while
> > sending 1G traffic after some minutes
> >
> > Hello Mates/OLE/Dave,
> >
> > I have an important query on "show dpdk buffers" allocation. I have only
> 1
> > NUMA node on my PC and buffers-per-numa is increased from 16800 (default)
> > to 128000. I am sending 1G Traffic and after some minutes there is "show
> > dpdk buffer" output where free becomes 0 and allocated becomes full. Have
> > seen this increasing slowly with time.
> > Why is there no refresh of buffers and all are allocated slowly ? Please
> > advise. This is a serious issue as this is a performance impact and I
> need
> > to find out the solution so please help.
> >
> > /Akash
>
-=-=-=-=-=-=-=-=-=-=-=- Links: You receive all messages sent to this group. View/Reply Online (#20316): https://lists.fd.io/g/vpp-dev/message/20316 Mute This Topic: https://lists.fd.io/mt/86230891/21656 Group Owner: [email protected] Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub [[email protected]] -=-=-=-=-=-=-=-=-=-=-=-
