> > > > > -----Message d'origine----- > > > De : Alan Cox [mailto:alan@xxxxxxxxxxxxxxxxxxx] > > > > > BTW, here is the hdparm using the old driver: Wrong key... Here is the output of hdparm: OLD DRIVER: ----------- [root@kayak /root]# hdparm -T -t /dev/hda /dev/hda: Timing cached reads: 4816 MB in 2.00 seconds = 2408.44 MB/sec Timing buffered disk reads: 12 MB in 3.23 seconds = 3.72 MB/sec LIBATA: ------- [root@kayak /root]# hdparm -T -t /dev/sda /dev/sda: Timing cached reads: 4960 MB in 2.00 seconds = 2480.38 MB/sec Timing buffered disk reads: 168 MB in 3.00 seconds = 55.94 MB/sec And Alan, you where right... The load average did grew up has much using libata vs old-ide... The main difference was that the system was still responsive (unles trying to make a parallel write/read on that same disk) and it actually finished up writing 10000 1mb file a few mins (instead of me stopping the test after 15 minutes and only around 1500 files written down). - vin - To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
