Joe Little
2006-Sep-11 23:40 UTC
[dtrace-discuss] Looking for common dtrace scripts for NFS top talkers
We started seeing odd behaviour with clients somehow hammering our ZFS-based NFS server. Nothing is obvious from mpstat/iostat/etc. I''ve seen mention before of NFSv3 client dtrace scripts, and I was wondering if there ever was one for the server end, displaying top talkers, writes/reads, or locations of such to nail down abusive clients short of using snoop/tcpdump to nail down via decoding NFS who is doing what.
eric kustarz
2006-Sep-12 17:41 UTC
[dtrace-discuss] Re: [nfs-discuss] Looking for common dtrace scripts for NFS top talkers
This should get you what you want now: blogs.sun.com/erickustarz/date/20050503 In the near(?) future, this will be a lot nicer to do via: opensolaris.org/os/project/nfs4trace eric Joe Little wrote:> We started seeing odd behaviour with clients somehow hammering our > ZFS-based NFS server. Nothing is obvious from mpstat/iostat/etc. I''ve > seen mention before of NFSv3 client dtrace scripts, and I was > wondering if there ever was one for the server end, displaying top > talkers, writes/reads, or locations of such to nail down abusive > clients short of using snoop/tcpdump to nail down via decoding NFS who > is doing what. > _______________________________________________ > nfs-discuss mailing list > nfs-discuss at opensolaris.org
Maybe Matching Threads
- Nested Resources vs. Normal Resources
- Re: Hardware for handling large call volume
- xcalls - mpstat vs dtrace
- how to debug context switching and mutex contentions?
- Under DTrace USDT and PID, kernel''s microstat accounting doesn''t work in this situation, doesn''t it?