Bug 1415647

Summary:	[scale] - lower network resources comparing to 4.0
Product:	[oVirt] ovirt-engine	Reporter:	Eldad Marciano <emarcian>
Component:	Backend.Core	Assignee:	Nobody <nobody>
Status:	CLOSED NOTABUG	QA Contact:	meital avital <mavital>
Severity:	medium	Docs Contact:
Priority:	unspecified
Version:	4.1.0.1	CC:	bugs
Target Milestone:	---
Target Release:	---
Hardware:	x86_64
OS:	Linux
Whiteboard:
Fixed In Version:		Doc Type:	If docs needed, set a value
Doc Text:		Story Points:	---
Clone Of:		Environment:
Last Closed:	2017-01-23 11:02:49 UTC	Type:	Bug
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	Infra	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description Eldad Marciano 2017-01-23 10:45:08 UTC

Description of problem:
in part of scale up 4.1 testing we found lower rate of network sent recv bytes.

I submit this as a bug in order to make sure that anything didn't broken.

we need to clarify if some changes made around: 
- engine db queries results set. 
- engine db queries invocations (caching).
- vdsm api calls results set
- vdsm api invocations (caching)

Version-Release number of selected component (if applicable):
4.0.1-0.3

How reproducible:
100%

Steps to Reproduce:
1. scale up scenario of 1 host 1 SD and ramp up of 111 vms.
2. monitor the env for 12 hours.

Actual results:
lower network traffic were monitored

Expected results:
we expect to have better performance for build to build.
currently we suspect that lower rate as a bug and not as enhancement.

Additional info:

Comment 2 Yaniv Kaul 2017-01-23 11:02:49 UTC

Closing. There's hardly anything we can do with this bug.
There were tens, if not more of changes performed.
For example, the 4.1 SDK is compressing by default, while 4.0 doesn't - did you use 4.1 SDK against 4.1 and 4.0 SDK against 4.0? (this is just an example, I believe you are using direct REST - which also, depending on the client, may or may not compress).