<div dir="ltr">I'm having trouble understanding your issue. Does your ramdisk only allocate backing memory on demand? (ie. is the ramdisk itself a thinly provisioned device?). If so, not supporting discard seems to be the problem.<div><br></div><div>Thinp makes no promises about where it will allocate your data. If you write a file, delete it, discard and then rewrite the file there is no guarantee that the file will be written to the same location.</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Tue, Mar 1, 2022 at 2:08 PM luomeng <<a href="mailto:luomeng12@huawei.com">luomeng12@huawei.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Because thin-pool is storage over-commitment, one of the following <br>
scenarios exists: constantly create and delete file, then the search <br>
doesn't hit the end of the metadata device, but ramdisk hits the end <br>
(not support discard). So the cursor doesn't reset.<br>
<br>
在 2022/2/28 23:37, Mike Snitzer 写道:<br>
> What you're saying doesn't make any sense. Especially when you<br>
> consider this last part of the commit message:<br>
> "Fix these issues by leaving the cursor alone, only resetting when the<br>
> search hits the end of the metadata device."<br>
<br>
</blockquote></div>