Message161121
| Author |
hynek |
| Recipients |
amcnabb, hynek, loewis, neologix, r.david.murray |
| Date |
2012年05月19日.14:20:32 |
| SpamBayes Score |
-1.0 |
| Marked as misclassified |
Yes |
| Message-id |
<4FB7AC30.3080002@ox.cx> |
| In-reply-to |
<20120519161719.Horde.1cZiEUlCcOxPt6tvZ5ZXd3A@webmail.df.eu> |
| Content |
>>> """
>>> stat("/net/prodigy", {st_mode=S_IFDIR|0755, st_size=4096, ...}) = 0
>>> mkdir("/net/prodigy/tmp", 0777) = -1 EACCES (Permission denied)
>>> """
>>>
>>> As you can see, a stat() is already done on /net/prodigy.
>>
>> To be fair, that shouldn’t trigger a mount. Otherwise a `ls -l` on /net
>> would mount all volumes.
>
> Not sure what "that" is: my view is that mkdir should trigger the mount,
> /net/prodigy is already there and available. ls -l doesn't invoke mkdir(2),
> so you wouldn't get a mount storm when it is mkdir that triggers the mount.
Sure, I was refering (as I hoped that my quoting would indicate) to the
stat on /net/prodigy, not the mkdir. I commented on the mkdir in the
next paragraph. |
|