Common causes of performance problems and outages
ahuja at wibh.net
Fri Jul 6 19:16:29 UTC 2001
In case folks are interested....
Craig and I did some work in this area some years ago...
Our findings appeared in FTCS 99 and are available at
requires digital library access). I also have a pointer to the U-M
techreport version at http://www.merit.edu/~ahuja/CSE-TR-382-98.pdf.
We have continued to collect more data on this and are in the process of
putting together our follow-up. It should be out soon.
We'd love to get more community input and more sources of data if folks
are willing to participate in our further studies...
On Fri, 6 Jul 2001, Avi Freedman wrote:
> In article <10162.15117.22199 at avi.netaxs.com> Sean wrote:
> : In roughly the order
> : 1. Network Engineers (What's this command do?)
> : 2. Power failures (What's this switch do?)
> : 3. Cable cuts (Backhoes, enough said)
> : 4. Hardware failures (What's that smell?)
> : 5. Congestion (More Bandwidth! Captain, I'm giving you all she's got!)
> : 6. Attacks (malicious, you know who you are)
> : 7. Software bugs (Your call is very important to us....)
> Very much disagree. Or at least, separate performance and outages.
> (Tie for 1st):
> 1) Shitty software from Major Router Vendors (and everyone else)
> 1) Misconfiguration
> a) Often caused by shitty/easy to fumble CLIs from Major Router Vendors
> 2) Attacks
> 3) Power failures
> 4) Cable cuts
> 5) (distant)Hardware failure
> Performance has been covered; the only real broadband is Universities,
> and relatively few transit networks can get to network large and small well.
More information about the NANOG