linux-kernel - Re: [PATCH 2/2] erofs: support to readahead dirent blocks in erofs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <2d772d8b-1314-4af6-b17a-b5f09acbf25b@kernel.org>
Date: Thu, 10 Jul 2025 21:15:10 +0800
From: Chao Yu <chao@...nel.org>
To: Gao Xiang <hsiangkao@...ux.alibaba.com>, xiang@...nel.org
Cc: chao@...nel.org, linux-erofs@...ts.ozlabs.org,
 linux-kernel@...r.kernel.org, Yue Hu <zbestahu@...il.com>,
 Jeffle Xu <jefflexu@...ux.alibaba.com>, Sandeep Dhavale
 <dhavale@...gle.com>, Hongbo Li <lihongbo22@...wei.com>
Subject: Re: [PATCH 2/2] erofs: support to readahead dirent blocks in
 erofs_readdir()

On 7/10/25 16:04, Gao Xiang wrote:
> 
> 
> On 2025/7/10 15:59, Chao Yu wrote:
>> On 7/10/25 15:46, Gao Xiang wrote:
>>> Hi Chao,
>>>
>>> On 2025/7/10 15:36, Chao Yu wrote:
>>>> This patch supports to readahead more blocks in erofs_readdir(),
>>>> it can enhance performance in large direcotry.
>>>>
>>>> readdir test in a large directory which contains 12000 sub-files.
>>>>
>>>>          files_per_second
>>>> Before:        926385.54
>>>> After:        2380435.562
>>>>
>>>> Signed-off-by: Chao Yu <chao@...nel.org>
>>>> ---
>>>>    fs/erofs/dir.c      | 8 ++++++++
>>>>    fs/erofs/internal.h | 3 +++
>>>>    2 files changed, 11 insertions(+)
>>>>
>>>> diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c
>>>> index cff61c5a172b..04113851fc0f 100644
>>>> --- a/fs/erofs/dir.c
>>>> +++ b/fs/erofs/dir.c
>>>> @@ -47,8 +47,10 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
>>>>        struct inode *dir = file_inode(f);
>>>>        struct erofs_buf buf = __EROFS_BUF_INITIALIZER;
>>>>        struct super_block *sb = dir->i_sb;
>>>> +    struct file_ra_state *ra = &f->f_ra;
>>>>        unsigned long bsz = sb->s_blocksize;
>>>>        unsigned int ofs = erofs_blkoff(sb, ctx->pos);
>>>> +    unsigned long nr_pages = DIV_ROUND_UP_POW2(dir->i_size, PAGE_SIZE);
>>>>        int err = 0;
>>>>        bool initial = true;
>>>>    @@ -65,6 +67,12 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx)
>>>>            }
>>>>            cond_resched();
>>>>    +        /* readahead blocks to enhance performance in large directory */
>>>> +        if (nr_pages - dbstart > 1 && !ra_has_index(ra, dbstart))
>>>> +            page_cache_sync_readahead(dir->i_mapping, ra, f,
>>>> +                dbstart, min(nr_pages - dbstart,
>>>> +                (pgoff_t)MAX_DIR_RA_PAGES));
>>>> +
>>>>            de = erofs_bread(&buf, dbstart, true);
>>>>            if (IS_ERR(de)) {
>>>>                erofs_err(sb, "failed to readdir of logical block %llu of nid %llu",
>>>> diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
>>>> index a32c03a80c70..ef9d1ee8c688 100644
>>>> --- a/fs/erofs/internal.h
>>>> +++ b/fs/erofs/internal.h
>>>> @@ -238,6 +238,9 @@ EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER)
>>>>    #define EROFS_I_BL_XATTR_BIT    (BITS_PER_LONG - 1)
>>>>    #define EROFS_I_BL_Z_BIT    (BITS_PER_LONG - 2)
>>>>    +/* maximum readahead pages of directory */
>>>> +#define MAX_DIR_RA_PAGES    4
>>>
>>> Could we set it as a per-sb sysfs configuration for users to config?
>>
>> Xiang,
>>
>> Oh, that will be better, how about introducing new sysfs in separated patch?
> 
> Hi Chao,
> 
> Thanks for your interest but in that case it could cause some bisect
> issue anyway, could we just use one patch to add this optimization
> for slow devices?

Xiang,

Yeah, one patch includes all these looks fine to me, anyway, let me update v2.

Thanks,

> 
> Thanks,
> Gao Xiang
> 
>>
>> Thanks,
>>
>>>
>>> Thanks,
>>> Gao Xiang
>>
>