Hi All. A colleague and I have been puzzling over a server that temporarily freezes (bringing the load average up something terrible!) every now and then when there is a lot of HD writing going on (it uses ultra-super-duper-fast SCSI drives on an adaptec 3400 RAID card) After a minute of intense HD activity (and a state in which no processes seem to be able to do anything - you pretty much think the system has frozen), the system returns to normal (with the exception of the backlogged-processes, hence the through-the-ceiling load average) Anyhow, this (from the reiserfs FAQ) MAY be the issue: "Why do things freeze on my IDE hard drive for annoying amounts of time? Because when large writes are scheduled all at once, reads can starve. A fix for this is evolving; the later your ReiserFS patch, the better we handle this. " All well and good on a cheapie IDE drive, but this is just ridiculous on a top-of-the-range SCSI solution!! I mean, what's the use having a great multitasking OS if your file system essentially doesnt allow that multitasking? The FS should now allow one process to hog the read/write/both queue!! (I even nice'd the cp and it had no affect) I have patched reiserfs using yast2 (patch 574) and the problem persists. Has anybody come accross this problem, or have any insight into it? Regards, Keith