> > Neil, Thanks for the info but I am kinda confused as to why the sudden > > writeout occurs at 4 minutes if the default ext3 settings is to flush > > the journal every 5 seconds. Do you know what the correlation between > > these times would be. > > I'm not sure. > There is a bug in some kernels where the time stamp of some blocks is > wrong, so old data doesn't get flushed out by bdflush when it should. > This can mean that data older than the bdflush interval stays in > memory until it is forced out by the journal being full. > > Maybe your average data rate fills the journal in about 4 minutes, and > the other bug is interfering with the regular bdflush writeout of data > blocks. > > What kernel are you running? Are you using any ext3 patches on top of > it? This is Redhat 7.3 with kernel 2.4.18-26.7 on a dual Xeon 1.8 Ghz with 2GB memory The only change we did was to enable the highmem-io patch for the 3ware card in the kernel.spec file. The patch is written by bcrl and is disabled by default in the RH kernel. I'll lose the I/O performance if I don't enable it since I have > 1GB memory, the bounce-buffer copying is going to hurt > NeilBrown > > > > I have seen previous posts from you in which you described your > > fileservers also having write stalls at around 5 minute intervals. Did > > you figure out why things would go bad at 5 minutes interval. There > > seems to be no default writeout every 5 minutes > > I don't clearly remember, but I don't think I found anything that > clearly pointed to 5 minutes being significant. > -- Yusuf Goolamabbas Reasons to switch to FireBird yusufg@outblaze.com http://mozilla.org/projects/phoenix/why/index.html _______________________________________________ Ext3-users@redhat.com https://listman.redhat.com/mailman/listinfo/ext3-users
