Re: [dpdk-dev] [dpdklab] Re: [dpdk-ci] [CI] SPDK compilation failures @ DPDK community lab

From: Zawadzki, Tomasz <hidden>
Date: 2021-02-17 16:06:51

Hi folks,

Patch in question is now part of v21.01.x branch and tests in UNH lab can make use of it.
https://github.com/spdk/spdk/commit/14eeeea669010247fa8d6c7ce53b2e69fcfaa858

If possible, removing '--without-vhost' would be best going forward. Then SPDK compilation tests would cover rte_vhost too.

Thanks,
Tomek

-----Original Message-----
From: Aaron Conole <aconole@redhat.com>
Sent: Monday, February 15, 2021 4:28 PM
To: Brandon Lo <redacted>
Cc: Zawadzki, Tomasz <redacted>; Lincoln Lavoie
[off-list ref]; dpdklab@iol.unh.edu; ci@dpdk.org; dev@dpdk.org;
spdk@lists.01.org
Subject: Re: [dpdklab] Re: [dpdk-ci] [dpdk-dev] [CI] SPDK compilation failures
@ DPDK community lab

Brandon Lo [off-list ref] writes:

quoted

Hi Tomek,

I do not think we have a specific reason for disabling vhost. I can
look into enabling it and get back to you on that.

I did a test, but I had to hack up the dockerfile and compile script a bit.

I removed the '--without-vhost' (I also modified it to pull dpdk and SPDK from
their respective 'main'/'master' branches).  The build completed successfully.

I will update the BZ with this information.  Can you try testing with the '--
without-vhost' removed from the compile_spdk.sh line, and if that is
successful we can modify the job and re-enable?

quoted

Thanks,
Brandon

On Fri, Feb 12, 2021 at 4:18 AM Zawadzki, Tomasz
[off-list ref] wrote:

quoted

Hi,

As Aaron noted this was result of rte_ethdev depending on rte_net.
On SPDK side rte_net was included in default compilation with vhost
component, but since vhost is disabled in the UNH lab tests with SPDK
it showed up as missing. A fix for that is now submitted to
SPDK:
https://review.spdk.io/gerrit/c/spdk/spdk/+/6398
I'll let you know when it makes it's way to the v21.01.x branch.

@Brandon Lo General question, is there particular reason to disable
vhost [configure argument '--without-vhost'] in the UNH lab tests
with SPDK ?
I don't recall any identified issue and enabling it would increase
the coverage of the compilation tests.

Thanks,
Tomek

quoted

-----Original Message-----
From: Aaron Conole <aconole@redhat.com>
Sent: Thursday, February 11, 2021 3:02 PM
To: Brandon Lo <redacted>
Cc: Zawadzki, Tomasz <redacted>; Lincoln Lavoie
[off-list ref]; dpdklab@iol.unh.edu; ci@dpdk.org;
dev@dpdk.org; spdk@lists.01.org
Subject: Re: [dpdklab] Re: [dpdk-ci] [dpdk-dev] [CI] SPDK
compilation failures @ DPDK community lab

Brandon Lo [off-list ref] writes:

quoted

Hi again everyone,

I have checked the pipelines with SPDK branch v21.01.x on the
main DPDK

branch.

quoted

It still seems to have an issue with compilation, and I have
attached a log of a Fedora SPDK compilation.
There are some undefined references to "rte_ether_unformat_addr"
I will continue to look into this. If you have any ideas on how
to fix this, please let me know.

Looks like rte_ethdev depends on rte_net - maybe I missed something.

Brandon, can we disable this test for the time being since it's
been failing for a while now?  Can you also send me the container
image / definitions you're using so that I can help work on this?

quoted

Thanks,
Brandon

On Tue, Feb 9, 2021 at 11:07 AM Brandon Lo [off-list ref]

wrote:

quoted

Hi everyone,

I will adjust the branches and watch over the first few
pipelines to make sure everything goes smoothly.

Thanks for the update,
Brandon

On Tue, Feb 9, 2021 at 10:13 AM Aaron Conole
[off-list ref]

wrote:

quoted

"Zawadzki, Tomasz" [off-list ref] writes:

quoted

Hi Lincoln,



That patch in question is now merged to branch v21.01.x.

Good to know - I do still see a failure in the IOL job (even
from a few hours ago).  I suppose the lab side might need some
adjustment,

too?

quoted

The builds performed for latest SPDK and SPDK LTS, against
dpdk-main branch seem to be passing. Would love to hear if
this is what you are seeing on your end too.



Thanks,

Tomek



From: Lincoln Lavoie <redacted>
Sent: Monday, February 8, 2021 5:21 PM
To: Zawadzki, Tomasz <redacted>
Cc: Aaron Conole <aconole@redhat.com>; Brandon Lo
[off-list ref]; dpdklab@iol.unh.edu; ci@dpdk.org;
dev@dpdk.org; spdk@lists.01.org
Subject: Re: [dpdk-ci] [dpdk-dev] [CI] SPDK compilation
failures @ DPDK community lab



Thanks Tomek,



Can you let us know when the merge happens and we'll make
sure the next set of builds pass or see what the next
failure is. :-P



Cheers,
Lincoln



On Mon, Feb 8, 2021 at 11:03 AM Zawadzki, Tomasz

[off-list ref] wrote:

quoted

 Hi Aaron,

 Thank you for reporting this !

 This is an issue with rte_power now depending on
rte_ethdev, which

was resolved on latest SPDK.

quoted

 I believe that UNH lab verifies DPDK patches against SPDK
branch for latest release. Which after the very recent SPDK
release, would be v21.01.x:
 https://github.com/spdk/spdk/tree/v21.01.x

 The fix has been backported to that branch and should be
merged

shortly:

quoted

 https://review.spdk.io/gerrit/c/spdk/spdk/+/6320

 Thanks,
 Tomek

 > -----Original Message-----  > From: dev
[off-list ref] On Behalf Of Aaron Conole  >
Sent: Monday, February 8, 2021 4:21 PM  > To: Brandon Lo
[off-list ref]  > Cc: dpdklab@iol.unh.edu; ci@dpdk.org;
dev@dpdk.org; spdk@lists.01.org  > Subject: [dpdk-dev] [CI]
SPDK compilation failures @ DPDK community lab  >  >
Greetings,  >  > I've noticed that recently SPDK compilation
in the UNH community lab seems  > to be failing, and I don't
see an obvious reason for the

failure.

quoted

 > The logs haven't been too helpful - it appears that there
is a symbol that isn't  > available when linking.
 >
 > Job details (for example):
 > https://lab.dpdk.org/results/dashboard/results/results-
 >

uploads/test_runs/2363efb43157465db3228c34c00ebd57/log_upload_fil

quoted

e/20  >
21/2/dpdk_f6f2d2240153_15524_2021-02-04_22-59-59_NA.zip
 >
 > Is it possible to turn on more verbose logging during the
compilation of  > SPDK?  Maybe show the arguments to the
compiler

for the specific object?

quoted

 > Maybe the SPDK folks can see something obviously wrong?
 >
 > Thanks,
 > -Aaron


--

Brandon Lo

UNH InterOperability Laboratory

21 Madbury Rd, Suite 100, Durham, NH 03824

blo@iol.unh.edu

www.iol.unh.edu

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help