Bug 639790

Summary: Performance Tuning Guide: TRACKING BUG for [I/O] [Asynchronous I/O]
Product: Red Hat Enterprise Linux 6 Reporter: Don Domingo <ddomingo>
Component: doc-Performance_Tuning_GuideAssignee: Laura Bailey <lbailey>
Status: CLOSED CURRENTRELEASE QA Contact: ecs-bugs
Severity: medium Docs Contact:
Priority: low    
Version: 6.1CC: ddomingo, srao
Target Milestone: rcKeywords: Documentation, Tracking
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: 6.1 Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2011-07-04 01:51:48 UTC Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Bug Depends On:    
Bug Blocks: 639779    

Comment 9 Sanjay Rao 2011-02-14 17:42:47 UTC
Looks good.

Comment 10 Sanjay Rao 2011-02-14 17:44:27 UTC
I had these comments

Please take out the line "This allows an application to perform I/O on multiple sources simultaneously. " from the first para. Synchronous IO also works on multiple sources. The IO wait is on a per device basis so if an IO is issued to a device, synchronous IO waits for that IO to complete before issuing another IO to the device. If you want you can change it to "This allows an application to issue multiple IOs to a device and continue with its operation"



Your comment
Sanjay: do we need to explain the sudden drop in delta from 60U to 80U? or am i reading the graph incorrectly?

My response - The drop in the difference is because of user contention. It is common among database applications to see run to run variation of a couple of percent. If you look closely, the blue bar dropped a bit and the orange bar went up a bit so the delta dropped. We can either mention that or modify the graph to take out the 80 user run.

Comment 11 Don Domingo 2011-02-16 04:13:50 UTC
thanks Sanjay, edited accordingly. please review:
http://documentation-stage.bne.redhat.com/docs/en-US/Red_Hat_Enterprise_Linux/6/html/Performance_Tuning_Guide/s-storage-asyncio.html

i'll just leave the graph as-is.


please advise if the section is good to go, and i will set it to MODIFIED. thanks!

Comment 12 Sanjay Rao 2011-02-16 11:42:28 UTC
Looks good.

Comment 15 Michael Doyle 2011-05-06 03:39:24 UTC
Verified based on c#12 in Red_Hat_Enterprise_Linux-Performance_Tuning_Guide-6-en-US-1.0-28