Skip to main content
Start a Conversation

Unsolved

This post is more than 5 years old

ramsdell

10 Posts

4150

February 18th, 2016 11:00

Slow Drains impact on your SAN

See this recent blog post by Erik Smith (@provandal) regarding the impact of Slow Drain conditions on your SAN.

     "If you work with Fibre Channel on a regular basis and have come to depend on its excellent performance attributes, you might be surprised to learn that many of the cases handled by our SAN team in Customer Support are related to performance problems.  Typically, as we dig into these cases, we discover the majority of them are not actually caused by the FC switches themselves, but rather by end devices that are not performing as expected and are causing fabric wide congestion.  These misbehaving end devices are referred to as “slow drains” and they represent a well-known class of problem that is inherent to all lossless transports including FC, DCB Ethernet (e.g., FCoE, RoCE) and even wastewater drain systems (e.g., “Plumbing”)."

     http://brasstacksblog.typepad.com/brass-tacks/2016/02/slow-drains-are-impacting-your-san.html

Anonymous

5 Practitioner

 • 

274.2K Posts

February 18th, 2016 14:00

DCNM 7.2(1) for SAN, released by EMC in August, 2015, added some new Slow Drain detection and avoidance features to the DCNM SAN client and Device Manager tools. This allows the user to monitor for:

  • E/F port congestion drops
  • F-port congestion drops
  • E/F slow-port monitoring

Click here for more info:

http://www.cisco.com/c/en/us/products/collateral/cloud-systems-management/prime-data-center-network-manager/bulletin-c25-735417.html

ramsdell

10 Posts

February 19th, 2016 06:00

Through FPI and MAPS, features of Brocade Fabric Vision technology, the following actions are available for Slow Drain device conditions via FOS v7.4:

  • Slow drain device quarantine action for Fabric Performance Impact (FPI) monitoring
    • FOS v7.4 provides a MAPS action that automatically isolates Slow Drain devices when they are detected by FPI monitoring.  This frees up buffer credits for normal devices that are sharing the same links and mitigates the effect due to presence of Slow Drain devices in the fabric
  • Port toggle action for Fabric Performance Impact monitoring
    • FOS v7.4 provides Port Toggle as an action which automatically recovers Slow Drain device conditions when they are detected by FPI monitoring.  A port toggle (which is a port disable followed by a port enable) can recover the ports from some Slow Drain device conditions or force traffic failover to an alternate path.

Click here for more info:

https://www.brocade.com/content/dam/common/documents/content-types/faqs/brocade-fabric-vision-faq.pdf

Ed Schulte

148 Posts

February 26th, 2016 06:00

The Slow Drain Knowledge Map is also on EMC support, in the following KB article;

464027 : Slow Drain Knowledge Map:

https://support.emc.com/kb/464027

ramsdell

10 Posts

February 26th, 2016 09:00

Thanks Ed!  The diagram reinforces some of the inherent complications and time in manual diagnosis of Slow Drain conditions across a SAN.  Efficient use of the tools can lead to quicker remediation.

Anonymous

5 Practitioner

 • 

274.2K Posts

March 28th, 2016 14:00

EMC offers professional services to help you proactively manage and optimize your SAN to prevent slow draining devices from impacting your network. Please contact your EMC Sales Rep today to learn more.

View More

View All

No Events found!

Top