Bug 129998

Summary: NFS via TCP
Product: [Fedora] Fedora Reporter: Jochen Witte <jwitte>
Component: glibcAssignee: Jakub Jelinek <jakub>
Status: CLOSED NOTABUG QA Contact: Brian Brock <bbrock>
Severity: medium Docs Contact:
Priority: medium    
Version: 2   
Target Milestone: ---   
Target Release: ---   
Hardware: i686   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2004-08-17 13:38:03 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:
Attachments:
Description Flags
trace of a mount / ls none

Description Jochen Witte 2004-08-16 14:54:51 UTC 
Description of problem:
I wrote a little user-space NFS-Server, which works just fine over
UDP. However, trying TCP results in retransmits of REPLIES and the
whole thing gets very very slow.

When I try the kernel NFSD everything works correctly. What do I have
to do, to use RPC over TCP correctly? I know, this seems not to be a
distribution bug, but since the GLIBC guys say: "first report the
'bug' to Your distribution bug-tracking-system" -- I ended up here ;)

Version-Release number of selected component (if applicable):
2.3.3

How reproducible:
Well - compile my NFS-Server and try mounting it via TCP :)

Steps to Reproduce:
1.
2.
3.
  
Actual results:


Expected results:


Additional info:
Comment 1 Jochen Witte 2004-08-16 14:56:48 UTC 
Created attachment 102762 [details]
trace of a mount / ls

attachment is a libpcap file for use with tcpdump/ethreal
Comment 2 Jakub Jelinek 2004-08-17 13:38:03 UTC 
What does this have to do with glibc and where is a bug we should
look into?
If you are writing your application, then it is up to you to debug
why it is slow and only when you find out why if you suspect a bug
in something other than your application file a bug with all the details
you found out and why you think there is a bug.