On 06/09/2011 08:43 PM, Wu Fengguang wrote: >>> It's definitely a problem that cfq delays async writes too much. >>> However in Carlos's report, >>> >>> https://bugzilla.kernel.org/attachment.cgi?id=61222 >>> >>> there are no sync(1) or fsync running at all. So it may be indicating >>> a different problem. >> >> If you have a heavy read load we still need to write back timestamps, >> and it kinda sounds like he's hitting that. No guarantee that actuall >> is the cause, though. > > Right, in the other email I do find the reads. > > So Carlos, it's worthwhile to try the deadline scheduler, which will > at least improve read/write workloads (likely the one you are running) > that don't involve sync/fsync. yes, deadline scheduler surely should help in this cases. Regards, Tao -- To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
