http://bugzilla.kernel.org/show_bug.cgi?id=10846 ------- Comment #1 from anonymous@xxxxxxxxxxxxxxxxxxxx 2008-06-02 08:11 ------- Reply-To: James.Bottomley@xxxxxxxxxxxxxxxxxxxxx On Mon, 2008-06-02 at 07:57 -0700, bugme-daemon@xxxxxxxxxxxxxxxxxxx wrote: > Very easy: We also check for an untar of the kernel (5x slower) > debian-test:~# dd if=/dev/zero of=/root/test.cdrom bs=10k count=60000 > 60000+0 enregistrements lus > 60000+0 enregistrements écrits > 614400000 octets (614 MB) copiés, 1,17602 seconde, 522 MB/s > debian-test:~# uname -a > Linux debian-test.pr.univmed.fr 2.6.19.7 #1 SMP Fri May 30 15:55:50 > CEST 2008 > i686 GNU/Linux > > debian:~# dd if=/dev/zero of=test.cdrom bs=10k count=60000 > 60000+0 records in > 60000+0 records out > 614400000 bytes (614 MB) copied, 7.51225 seconds, 81.8 MB/s > debian:~# uname -a > Linux debian 2.6.22-4-vserver-686 #1 SMP Tue Feb 12 22:02:04 UTC 2008 > i686 > GNU/Linux What exactly is test.cdrom on? A single disk? If so, then your first result is definitely bogus. The maximum bandwidth of a single SAS link is 300 MB/s, so it looks like the kernel is either caching the write or has timing issues. For a direct to platter speed, the data sheet for your drive gives 55-89MB/s, so I'd say 81.8 is well within the range. James -- Configure bugmail: http://bugzilla.kernel.org/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are the assignee for the bug, or are watching the assignee. -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
