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

Message-ID: <c0e0b8ed-13b6-41a4-b978-ff4b8f5b2634@linux.alibaba.com>
Date: Thu, 10 Jul 2025 16:04:00 +0800
From: Gao Xiang <hsiangkao@...ux.alibaba.com>
To: Chao Yu <chao@...nel.org>, xiang@...nel.org
Cc: 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 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?

Thanks,
Gao Xiang

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