All of lore.kernel.org
 help / color / mirror / Atom feed
From: Shakeel Butt <shakeelb@google.com>
To: Khazhismel Kumykov <khazhy@google.com>
Cc: miklos@szeredi.hu, linux-fsdevel <linux-fsdevel@vger.kernel.org>,
	LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/3] fuse: on 64-bit store time in d_fsdata directly
Date: Wed, 21 Aug 2019 17:17:14 -0700	[thread overview]
Message-ID: <CALvZod44CHWEUxa4Mi7nRLfgyCnGgNAxso8SLA5xVoR=DdQiWw@mail.gmail.com> (raw)
In-Reply-To: <20190822000933.180870-1-khazhy@google.com>

On Wed, Aug 21, 2019 at 5:09 PM Khazhismel Kumykov <khazhy@google.com> wrote:
>
> Implements the optimization noted in f75fdf22b0a8 ("fuse: don't use
> ->d_time"), as the additional memory can be significant. (In particular,
> on SLAB configurations this 8-byte alloc becomes 32 bytes). Per-dentry,
> this can consume significant memory.
>
> Signed-off-by: Khazhismel Kumykov <khazhy@google.com>

Actually we are seeing this in production where a job creating a lot
of fuse files cause a lot of extra system level overhead.

Reviewed-by: Shakeel Butt <shakeelb@google.com>

> ---
>  fs/fuse/dir.c | 19 +++++++++++++++++++
>  1 file changed, 19 insertions(+)
>
> diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
> index dd0f64f7bc06..f9c59a296568 100644
> --- a/fs/fuse/dir.c
> +++ b/fs/fuse/dir.c
> @@ -24,6 +24,18 @@ static void fuse_advise_use_readdirplus(struct inode *dir)
>         set_bit(FUSE_I_ADVISE_RDPLUS, &fi->state);
>  }
>
> +#if BITS_PER_LONG >= 64
> +static inline void fuse_dentry_settime(struct dentry *entry, u64 time)
> +{
> +       entry->d_fsdata = (void *) time;
> +}
> +
> +static inline u64 fuse_dentry_time(struct dentry *entry)
> +{
> +       return (u64)entry->d_fsdata;
> +}
> +
> +#else
>  union fuse_dentry {
>         u64 time;
>         struct rcu_head rcu;
> @@ -38,6 +50,7 @@ static inline u64 fuse_dentry_time(struct dentry *entry)
>  {
>         return ((union fuse_dentry *) entry->d_fsdata)->time;
>  }
> +#endif
>
>  /*
>   * FUSE caches dentries and attributes with separate timeout.  The
> @@ -242,6 +255,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags)
>         goto out;
>  }
>
> +#if BITS_PER_LONG < 64
>  static int fuse_dentry_init(struct dentry *dentry)
>  {
>         dentry->d_fsdata = kzalloc(sizeof(union fuse_dentry), GFP_KERNEL);
> @@ -254,16 +268,21 @@ static void fuse_dentry_release(struct dentry *dentry)
>
>         kfree_rcu(fd, rcu);
>  }
> +#endif
>
>  const struct dentry_operations fuse_dentry_operations = {
>         .d_revalidate   = fuse_dentry_revalidate,
> +#if BITS_PER_LONG < 64
>         .d_init         = fuse_dentry_init,
>         .d_release      = fuse_dentry_release,
> +#endif
>  };
>
>  const struct dentry_operations fuse_root_dentry_operations = {
> +#if BITS_PER_LONG < 64
>         .d_init         = fuse_dentry_init,
>         .d_release      = fuse_dentry_release,
> +#endif
>  };
>
>  int fuse_valid_type(int m)
> --
> 2.23.0.187.g17f5b7556c-goog
>

      parent reply	other threads:[~2019-08-22  0:17 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-22  0:09 [PATCH 1/3] fuse: on 64-bit store time in d_fsdata directly Khazhismel Kumykov
2019-08-22  0:09 ` [PATCH 2/3] fuse: kmemcg account fs data Khazhismel Kumykov
2019-08-22  0:09 ` [PATCH 3/3] fuse: pass gfp flags to fuse_request_alloc Khazhismel Kumykov
2019-08-22  0:18   ` Shakeel Butt
2019-08-22 19:52     ` Khazhismel Kumykov
2019-08-22 19:52       ` Khazhismel Kumykov
2019-08-22  0:17 ` Shakeel Butt [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CALvZod44CHWEUxa4Mi7nRLfgyCnGgNAxso8SLA5xVoR=DdQiWw@mail.gmail.com' \
    --to=shakeelb@google.com \
    --cc=khazhy@google.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.