hi All,
I am running I/O from the ESX server to the storage device.If the packets are losed in between how will the ESX server detects the packet lost or data Over run and data underrun etc??
Regards,
SHILPA
The same way any ethernet device detects packet loss - TCP/IP packets are sequenced and when a packet is loss the missing packet is asked to be retransmitted -
If you find this or any other answer useful please consider awarding points by marking the answer correct or helpful
“Are there any tools that can help us debug I/O Commands within a ESX server itself ( Any layer of the stack from App->Intermediate Drivers->SCSI Stack->HBA Driver )”.
to add,,
Also, the idea is to capture transient errors ( Which could eventually succeed after retries ), but it would help to capture such events and predict failures down the line. One Ex: could be write command retries due to either OVERRUN/UNDERRUN flags not being set properly by the storage unit (or) disk sectors not proper (or) controller bottlenecks, ESX Server could have certain performance bottlenecks due to which a lot of queueing has happened, etc, etc
Hello,
For HBAs many of the errors actually appear within /var/log/vmkernel as they happen. You did ask about Network packet loss, now you have switched to HBAs. Which are we really discussing?
Best regards,
Edward L. Haletky VMware Communities User Moderator, VMware vExpert 2009
Virtualization Practice Analyst[/url]
Now Available: 'VMware vSphere(TM) and Virtual Infrastructure Security'[/url]
Also available 'VMWare ESX Server in the Enterprise'[/url]
[url=http://www.astroarch.com/wiki/index.php/Blog_Roll]SearchVMware Pro[/url]|Blue Gears[/url]|Top Virtualization Security Links[/url]|
[url=http://www.astroarch.com/wiki/index.php/Virtualization_Security_Round_Table_Podcast]Virtualization Security Round Table Podcast[/url]