Messages in this thread | | | Date | Sun, 05 Apr 2009 16:57:21 -0400 | From | Jeff Garzik <> | Subject | Re: [GIT PULL] Ext3 latency fixes |
| |
Mark Lord wrote: > Linus Torvalds wrote: >> >> Non-rotational media would tend to want the unplugging, but the block >> layer already does that (ie in __make_request() we already do: >> >> if (unplug || blk_queue_nonrot(q)) >> __generic_unplug_device(q); >> >> so non-rotational devices get unplugged whether the request was a >> unplugging request or not). > .. > > Mmm.. except that Jeff's SSD doesn't appear to identify itself > as a non-rotating media. I suppose there's a way to "quirk" that > somewhere, though.
We set it in libata-scsi.c:ata_scsi_dev_config() based on ata_id_is_ssd()
That hueristic probably assumes Intel SSDs or something :/
Jeff
| |