Bug #3783
Flow control is needed in rpcmod when the NFS server is unable to keep up with the network
| Status: | Closed | Start date: | 2013-05-23 | |
|---|---|---|---|---|
| Priority: | Normal | Due date: | ||
| Assignee: | % 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
#1
Updated by Marcel Telka about 1 year ago
Code review: https://www.illumos.org/rb/r/49/
#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