Ack, thanks! Fixed. -Jay
On Thu, Jul 11, 2013 at 2:22 PM, Roger Hoover <roger.hoo...@gmail.com>wrote: > Thank you, Jay. > > When talking about flush rates, I think you mean the opposite of what was > said here: > > "However very high application flush rates can lead to high latency when > the flush does occur." > > should be > > However very low application flush rates (infrequent flushes) can lead to > high latency when the flush does occur. > > Cheers, > > Roger > > > On Thu, Jul 11, 2013 at 12:36 PM, Jay Kreps <jay.kr...@gmail.com> wrote: > > > Probably it is very incomplete. I copied over much of the content from > 0.7 > > that is still applicable, but I added the following: > > 1. A section on data centers and mirroring > > 2. Removed the cut-and-pasted scala code in the monitoring section and > just > > gave a high-level description of what we monitor > > 3. Added a lot of details about what we have learned about Linux, ext3, > > write latency, etc. > > > > http://kafka.apache.org/08/ops.html > > > > Let me know any thoughts on how to improve this. > > > > -Jay > > >
