Re: [PATCH v2] exfat: speed up file creation in large directories

[Namjae Jeon]

> Test environment:
>   QEMU TCG multi-thread, 4 vCPUs, 6 GiB RAM
>   4 GiB exFAT image, 32 KiB clusters
>
> Test script:
>   mount -t exfat /dev/vda /mnt/test
>   time sh -c '
>           i=0
>           while [ "$i" -lt 20000 ]; do
>                   : > "/mnt/test/f.$i" || exit 1
>                   i=$((i + 1))
>           done
>   '
>
> The measured results were:
>
>                          Before          After
>   real                   589.48 s         5.33 s
>   user                     4.72 s         2.28 s
>   sys                    584.63 s         3.03 s
>
> The elapsed time was reduced by 99.10%, from 589.48 seconds to
> 5.33 seconds, corresponding to a 110.6-fold speedup.
Looks great!

> +                       for (len = 0; len < MAX_NAME_LENGTH && name.name[len]; len++)
> +                               ;
> +                       if (!len || len == MAX_NAME_LENGTH)
> +                               goto abort;
exfat allows filenames with 255 UTF16 code units, but this check
aborts filter construction. Any reason ?

> @@ -627,7 +666,8 @@ static int exfat_find(struct inode *dir, const struct qstr *qname,
>                 ei->hint_stat.clu = cdir.dir;
>                 ei->hint_stat.eidx = 0;
>                 ei->version = (inode_peek_iversion_raw(dir) & 0xffffffff);
> -               ei->hint_femp.eidx = EXFAT_HINT_NONE;
> +               if (!ei->name_filter)
> +                       ei->hint_femp.eidx = EXFAT_HINT_NONE;
There is no path that moves this hint backwards. exfat_unlink(),
exfat_rmdir(), __exfat_rename(), and the rollback path in
exfat_add_entry() free entries without updating ei->hint_femp. So,
exfat_find_empty_entry() can keep searching from a stale hint and
never reuse earlier holes. Repeated create/unlink operations may grow
the directory until MAX_EXFAT_DENTRIES.