On Sat, Jan 28, 2006 at 08:27:14PM +0100, Jens Axboe wrote: > On Fri, Jan 27 2006, Nix wrote: > > On 26 Jan 2006, Ariel noted: > > > Is this good or bad? I'm guessing it means it's still leaking. So it's > > > really starting to look like ata_piix is the problem. But we need someone > > > who has the leak to remove that and see if it helps. I can't, since my > > > drives are connected to it. > > > > FWIW, a bit of negative-confirmatory evidence: I have a sym53c875 > > and non-SATA IDE drive on this 2.6.15.1, and there is no leak, > > nor was there in 2.6.15: > > > > 11 11 100% 0.34K 1 11 4K scsi_cmd_cache > > It's not a bad data point, it just confirms that setting ->ordered_flush > to 0 in the SATA drivers will fix the leak. So really, it's as expected. > So far apparently nobody tried it, suggested it twice. > Are all sata drivers affected by this bug in 2.6.15? Any 'official' patch available? Or is the recommended workaround to set ordered_flush to 0 to fix this.. does that have any downsides? -- Pasi - : 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
