date:20181004

Re: [vpp-dev] Master branch l2bd test perf dop

2018-10-04 Thread Neale Ranns via Lists.Fd.Io

Hi Yuwei,

Can you test this, please:
https://gerrit.fd.io/r/#/c/15100/

thanks,
neale

De : "Zhang, Yuwei1" 
Date : vendredi 28 septembre 2018 à 03:08
À : "Neale Ranns (nranns)" , "vpp-dev@lists.fd.io" 

Objet : RE: [vpp-dev] Master branch l2bd test perf dop

Hi Neale,
 I assume the replications should related to the interfaces in the 
bridge, right? I just have 2 interfaces in the bridge which means one of the 
interface receive traffic and another send out. In the 64K size packet test 
case, the performance have almost 35% drop. I didn’t do other case yet.

Regards,
Yuwei
From: Neale Ranns (nranns) [mailto:nra...@cisco.com]
Sent: Thursday, September 27, 2018 8:31 PM
To: Zhang, Yuwei1 ; vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] Master branch l2bd test perf dop


Hi Yuwei,

There was a change to the l2flood node recently:
  https://gerrit.fd.io/r/#/c/13578/
where we use the buffer clone mechanism rather than free-recycle. I would 
expect the CPU cycles per invocation of the l2-flood node to increase, but the 
number of invocations of l2flood to decrease (w.r.t. the interface-tx node).
How many replications does your test perform and is there a trend for perf 
change versus number of replications?

Thanks,
Neale


De : mailto:vpp-dev@lists.fd.io>> au nom de Zhang Yuwei 
mailto:yuwei1.zh...@intel.com>>
Date : jeudi 27 septembre 2018 à 05:02
À : "vpp-dev@lists.fd.io" 
mailto:vpp-dev@lists.fd.io>>
Objet : [vpp-dev] Master branch l2bd test perf dop

Hi All,
 In our recent test, I found a performance drop in master branch. I 
execute the l2bd test case in a 2.5GHZ CPU and found almost 35% drop compared 
to 18.07 release. My test is set two NIC ports to a same bridge domain and send 
traffic to test the l2 forward performance. I found in the master branch, 
l2flood function consume much more CPU cycles than 18.07 which means any test 
use the l2flood function will also have a performance drop. Can anybody kindly 
help to check this issue? Thanks a lot.

Regards,
Yuwei

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#10756): https://lists.fd.io/g/vpp-dev/message/10756
Mute This Topic: https://lists.fd.io/mt/26289209/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] WRED

2018-10-04 Thread Dave Barach via Lists.Fd.Io

No luck reproducing the problem w/ multiple threads and 20 MPPS worth of 
traffic. The code involved doesn’t look trivially broken.

You might try setting a breakpoint in nsim_configure(...) and walk through it 
when you try to reconfigure the simulator with traffic flowing. I suppose an 
munmap accident might be involved, but I don’t see the problem.

HTH... Dave

From: vpp-dev@lists.fd.io  On Behalf Of Dave Barach via 
Lists.Fd.Io
Sent: Wednesday, October 3, 2018 6:10 PM
To: Brendan Kelly 
Cc: vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] WRED

OK, let me see if I can repro it...

From: Brendan Kelly mailto:brendanake...@yahoo.com>>
Sent: Wednesday, October 3, 2018 6:03 PM
To: Dave Barach (dbarach) mailto:dbar...@cisco.com>>
Cc: vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] WRED

This is what I gathered.  I need to figure out how to get on Jira.

vpp# show version verbose
Version:  v18.10-rc0~553-g2f54c27
Compiled by:  root
Compile host: o2.opiehome.com
Compile date: Tue Oct  2 16:58:15 MDT 2018
Compile location: /root/source/vpp/vpp
Compiler: GCC 7.3.1 20180303 (Red Hat 7.3.1-5)
Current PID:  5871
vpp# create bridge-domain 1
bridge-domain 1
vpp# show interface
  Name   IdxState  MTU (L3/IP4/IP6/MPLS) 
Counter  Count
TenGigabitEthernet82/0/0  1 down 9000/0/0/0
TenGigabitEthernet82/0/1  2 down 9000/0/0/0
local00 down  0/0/0/0
vpp# set interface state TenGigabitEthernet82/0/0 up
vpp# set interface state TenGigabitEthernet82/0/1 up
vpp# set interface l2 bridge TenGigabitEthernet82/0/0 1
vpp# set interface l2 bridge TenGigabitEthernet82/0/1 1
vpp# set nsim delay 10 ms bandwidth 10.1 gbit packet-size 128
Configured link delay 10.00 ms, 20.00 ms round-trip
Sim uses 26304512 bytes per thread, 157827072 bytes total
vpp# nsim enable-disable TenGigabitEthernet82/0/0 TenGigabitEthernet82/0/1
vpp# show nsim
Network simulator cross-connects TenGigabitEthernet82/0/0 and 
TenGigabitEthernet82/0/1
...inserting link delay of 10.00 ms, 20.00 ms round-trip
vpp# show interface
  Name   IdxState  MTU (L3/IP4/IP6/MPLS) 
Counter  Count
TenGigabitEthernet82/0/0  1  up  9000/0/0/0 rx packets  
   16299
rx bytes
20247116
tx packets  
   23927
tx bytes
22969807
drops   
2407
TenGigabitEthernet82/0/1  2  up  9000/0/0/0 rx packets  
   23946
rx bytes
22972583
tx packets  
   16239
tx bytes
20206975
drops   
3549
local00 down  0/0/0/0
vpp# set nsim delay 50 ms bandwidth 10.1 gbit packet-size 128

Program received signal SIGSEGV, Segmentation fault.
_dl_fixup (l=0x6df680, reloc_arg=28) at ../elf/dl-runtime.c:71
71   const char *strtab = (const void *) D_PTR (l, l_info[DT_STRTAB]);
(gdb)


On Wednesday, October 3, 2018, 8:48:01 AM MDT, Dave Barach via Lists.Fd.Io 
mailto:dbarach=cisco@lists.fd.io>> wrote:



Please send a backtrace. Here are some general bug reporting suggestions: 
https://wiki.fd.io/view/VPP/BugReports.



I’ve certainly reconfigured the simulator with traffic flowing without having 
the wheels fall off, but the code is brand-new.



Thanks... Dave





From: Brendan Kelly mailto:brendanake...@yahoo.com>>
Sent: Wednesday, October 3, 2018 10:39 AM
To: brendanake...@yahoo.com
Cc: Dave Barach (dbarach) mailto:dbar...@cisco.com>>; 
vpp-dev@lists.fd.io
Subject: Re: [vpp-dev] WRED



Hello Dave, if you change the nsim delay values on the fly it appears vpp 
crashes and all the state is lost.



Is this supported?  Should I file a bug?

If so what logs should I attach?

On Oct 3, 2018, at 08:07, Brendan Kelly via Lists.Fd.Io 
mailto:brendanakelly=yahoo@lists.fd.io>>
 wrote:

Ok, thanks for the input.  I have it working.



vpp# create bridge-domain 1

bridge-domain 1

vpp# show b

bfdbier   bond   bridge-domain  buffers

vpp# show bridge-domain 1

  BD-ID   Index   BSN  Age(min)  Learning  U-Forwrd   UU-Flood   Flooding  
ARP-Term   BVI-Intf

1   1  0 offonon

Re: [vpp-dev] classifier for policy based forwarding

2018-10-04 Thread JB

Argh, I had written up a response but accidentally sent it to only Sandeep

We've also hit a snag with this. We are attempting to send TCP traffic upwards 
to FRR for the purpose of using BGP but have hit this snag. We need BGP to not 
only update VPPs FIB but also to receive updates over BGP via VPPs link nets 
from neighbouring routers.

If the group has a better suggestion for this, please do tell.

We can't seem to find a clear point when this was changed, or if it's a current 
bug. This part of the issue seems to fall under vpp-dev and not vppsb-dev.
-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#10754): https://lists.fd.io/g/vpp-dev/message/10754
Mute This Topic: https://lists.fd.io/mt/24602615/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] VAT api changes 5507192..8807674

2018-10-04 Thread Peter Mikus via Lists.Fd.Io

With latest version 18.10-rc0~572-g5958769~b5355 the issue is not there 
anymore. So I am considering this one as closed.

Peter Mikus
Engineer – Software
Cisco Systems Limited

From: Maciek Konstantynowicz (mkonstan)
Sent: Thursday, October 4, 2018 10:28 AM
To: Peter Mikus -X (pmikus - PANTHEON TECHNOLOGIES at Cisco) 
; vpp-dev@lists.fd.io
Cc: csit-dev 
Subject: Re: [vpp-dev] VAT api changes 5507192..8807674

Is it still broken?

-Maciek

On 3 Oct 2018, at 09:11, Peter Mikus via Lists.Fd.Io 
mailto:pmikus=cisco@lists.fd.io>> wrote:

Hello devs,

Recently in CSIT we are facing the issue with vpp_api_test console with JSON 
enabled, when calling dump_interface_table:

dump_interface_table:6017: JSON output supported only for VPE API calls and 
dump_stats_table
main:427: BUG: message reply spin-wait timeout

our API call:

$ sudo -S vpp_api_test json in dump_interfaces.vat script

Where:
$ cat dump_interfaces.vat
sw_interface_dump
dump_interface_table
quit

Brief bisecting reveals that its happening after one of these:

$ git log --pretty=oneline 5507192..8807674
88076749e663e35925c2212eb79e2ec4ce023772 (HEAD -> master, origin/master, 
origin/HEAD) Enabled untagged vs default functionality Removed 0-tags attribute 
for default-sub-if config Moved default-sub-if check before untagged
819d5fdb39526386ee8fe4a8729f960e84443cbd VPP-1440: clean up coverity warnings
bf49590c07162be44b21d0e0440e7fb96b2746d5 Stats: vpp_prometheus_export fixes.
94495f2a6a68ac2202b7715ce09620f1ba6fe673 PAPI: Use UNIX domain sockets instead 
of shared memory
84db4087fa38b8d4c62cbb0787d600950638034c vcl: fix coverity warning
c67cfd22bedf5b45e82ff6820d1d4e6f61ba5187 ip4-local: classify protos that skip 
csum and src check
2f54c27f7fd0d2c24e7d6b1d48809e8b58ec1abf vhost-user: add support for vlib_log 
API

Could you please take a look and let us know if this is bug or desired?

Thank you.

Peter Mikus
Engineer – Software
Cisco Systems Limited

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#10737): https://lists.fd.io/g/vpp-dev/message/10737
Mute This Topic: https://lists.fd.io/mt/26716121/675185
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  
[mkons...@cisco.com]
-=-=-=-=-=-=-=-=-=-=-=-

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#10753): https://lists.fd.io/g/vpp-dev/message/10753
Mute This Topic: https://lists.fd.io/mt/26716121/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] VAT api changes 5507192..8807674

2018-10-04 Thread Maciek Konstantynowicz (mkonstan) via Lists.Fd.Io

Is it still broken?

-Maciek

On 3 Oct 2018, at 09:11, Peter Mikus via Lists.Fd.Io 
mailto:pmikus=cisco@lists.fd.io>> wrote:

Hello devs,

Recently in CSIT we are facing the issue with vpp_api_test console with JSON 
enabled, when calling dump_interface_table:

dump_interface_table:6017: JSON output supported only for VPE API calls and 
dump_stats_table
main:427: BUG: message reply spin-wait timeout

our API call:

$ sudo -S vpp_api_test json in dump_interfaces.vat script

Where:
$ cat dump_interfaces.vat
sw_interface_dump
dump_interface_table
quit

Brief bisecting reveals that its happening after one of these:

$ git log --pretty=oneline 5507192..8807674
88076749e663e35925c2212eb79e2ec4ce023772 (HEAD -> master, origin/master, 
origin/HEAD) Enabled untagged vs default functionality Removed 0-tags attribute 
for default-sub-if config Moved default-sub-if check before untagged
819d5fdb39526386ee8fe4a8729f960e84443cbd VPP-1440: clean up coverity warnings
bf49590c07162be44b21d0e0440e7fb96b2746d5 Stats: vpp_prometheus_export fixes.
94495f2a6a68ac2202b7715ce09620f1ba6fe673 PAPI: Use UNIX domain sockets instead 
of shared memory
84db4087fa38b8d4c62cbb0787d600950638034c vcl: fix coverity warning
c67cfd22bedf5b45e82ff6820d1d4e6f61ba5187 ip4-local: classify protos that skip 
csum and src check
2f54c27f7fd0d2c24e7d6b1d48809e8b58ec1abf vhost-user: add support for vlib_log 
API

Could you please take a look and let us know if this is bug or desired?

Thank you.

Peter Mikus
Engineer – Software
Cisco Systems Limited

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#10737): https://lists.fd.io/g/vpp-dev/message/10737
Mute This Topic: https://lists.fd.io/mt/26716121/675185
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  
[mkons...@cisco.com]
-=-=-=-=-=-=-=-=-=-=-=-

-=-=-=-=-=-=-=-=-=-=-=-
Links: You receive all messages sent to this group.

View/Reply Online (#10752): https://lists.fd.io/g/vpp-dev/message/10752
Mute This Topic: https://lists.fd.io/mt/26716121/21656
Group Owner: vpp-dev+ow...@lists.fd.io
Unsubscribe: https://lists.fd.io/g/vpp-dev/unsub  [arch...@mail-archive.com]
-=-=-=-=-=-=-=-=-=-=-=-

Re: [vpp-dev] Master branch l2bd test perf dop

Re: [vpp-dev] WRED

Re: [vpp-dev] classifier for policy based forwarding

Re: [vpp-dev] VAT api changes 5507192..8807674

Re: [vpp-dev] VAT api changes 5507192..8807674

5 matches

Site Navigation

Mail list logo

Footer information