Messages in this thread | | | Date | Wed, 25 May 2022 17:07:08 +0200 | From | Thomas Weißschuh <> | Subject | Re: [PATCH] nvme-pci: fix host memory buffer allocation size |
| |
On 2022-05-10 12:20+0200, Thomas Weißschuh wrote: > [..] > > We could look into removing the min with > > PAGE_SIZE * MAX_ORDER_NR_PAGES to try to do larger segments for > > "segment challenged" controllers now that it could work on a lot > > of iommu enabled setups. But I'd rather have a very good reason for > > that. > > On my current setup (WD SN770 on ThinkPad X1 Carbon Gen9) frequently the NVME > controller stops responding. Switching from no scheduler to mq-deadline reduced > this but did not eliminate it. > Since switching to HMB of 1 * 200MiB and no scheduler this did not happen anymore. > (But I'll need some more time to gain real confidence in this)
So this patch dramatically improves the stability of my disk.
Without it and queue/scheduler=none the controller stops responding after a few minutes. mq-deadline reduced it to every few hours.
With the patch it happens roughly once a week.
I'll still RMA the disk and see if the replacement changes anything.
Maybe some of the Western Digital employees here could take a look or check if there is a new firmware available. (The official updater requires Windows and there is no external documentation about the firmware)
Not sure if a change from very broken to only slightly broken would be enough of a good reason to be honest.
Thomas
| |