Bug #3783

Flow control is needed in rpcmod when the NFS server is unable to keep up with the network

Added by Marcel Telka about 3 years ago. Updated about 1 year ago.

Status:ClosedStart date:2013-05-23
Priority:NormalDue date:
Assignee:Marcel Telka% Done:

100%

Category:nfs - NFS server and client
Target version:-
Difficulty:Medium Tags:needs-triage

Description

Some NFS clients (like Oracle dNFS) are known for very high retransmit rate with very short delay between RPC request retransmissions. Under some circumstances the incoming RPC requests rate might be so high that the NFS server will not be able to cope with them. Since the rpcmod module does not have any kind of flow control implemented, we might end up hoarding the incoming requests in svc queue(s). This could cause memory exhaustion of the NFS server memory.

To solve this issue we need to implement flow control in rpcmod.

History

#2 Updated by Marcel Telka about 1 year ago

  • Status changed from In Progress to Pending RTI

#3 Updated by Electric Monk about 1 year ago

  • % Done changed from 0 to 100
  • Status changed from Pending RTI to Closed

git commit 2695d4f4d1e2a6022c8a279d40c3cb750964974d

commit  2695d4f4d1e2a6022c8a279d40c3cb750964974d
Author: Marcel Telka <marcel.telka@nexenta.com>
Date:   2015-05-12T21:23:46.000Z

    3783 Flow control is needed in rpcmod when the NFS server is unable to keep up with the network
    Reviewed by: Gordon Ross <gordon.ross@nexenta.com>
    Reviewed by: Hans Rosenfeld <hans.rosenfeld@nexenta.com>
    Reviewed by: Dan McDonald <danmcd@omniti.com>
    Approved by: Albert Lee <trisk@omniti.com>

Also available in: Atom