Hello, On Friday, January 28, 2011 7:07 PM Rajaram R wrote: > On Fri, Jan 28, 2011 at 9:33 PM, Marek Szyprowski > <m.szyprowski@xxxxxxxxxxx> wrote: > > Hello, > > > > On Friday, January 28, 2011 4:31 PM Alan Stern wrote: > > > >> On Fri, 28 Jan 2011, Marek Szyprowski wrote: > >> > >> > This commit add code that flushed page cache disk buffers every 128 read > >> > and write request. It has almost no impact on the performance of the > >> > emulate usb drive but saves system page cache from being filled with > >> > useless emulated disk data. > > Could you also pls confirm the impact of this change on the > performance of the mass storage device? I've 2 series of tests: 1. copying about 1.5GB of small files to vfat partition 2. dd'ing one large (1GB) file directly to /dev/sdb. Before patch (average): 1. copying: 445s 2. copying: 125s After patch (average): 1. copying: 580s 2. copying: 188s The impact on the performance of the usb drive is noticeable. That's why this hack should be made optional or configurable. The main reason for a speed reduction is the fact that the pages are being written synchronously while processing host requests. I'm looking for a method for triggering mass storage page cache flush and invalidate that will be asynchronous. Best regards -- Marek Szyprowski Samsung Poland R&D Center -- To unsubscribe from this list: send the line "unsubscribe linux-usb" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
