diff mbox series

[PULL,26/26] virtiofsd: Add -o allow_direct_io|no_allow_direct_io options

Message ID 20200925120655.295142-27-dgilbert@redhat.com
State New
Headers show
Series [PULL,01/26] migration: Properly destroy variables on incoming side | expand

Commit Message

Dr. David Alan Gilbert (git) Sept. 25, 2020, 12:06 p.m. UTC
From: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>

Due to the commit 65da4539803373ec4eec97ffc49ee90083e56efd, the O_DIRECT
open flag of guest applications will be discarded by virtiofsd. While
this behavior makes it consistent with the virtio-9p scheme when guest
applications use direct I/O, we no longer have any chance to bypass the
host page cache.

Therefore, we add a flag 'allow_direct_io' to lo_data. If '-o
 no_allow_direct_io' option is added, or none of '-o allow_direct_io' or
 '-o no_allow_direct_io' is added, the 'allow_direct_io' will be set to
 0, and virtiofsd discards O_DIRECT as before. If '-o allow_direct_io'
is added to the starting command-line, 'allow_direct_io' will be set to
1, so that the O_DIRECT flags will be retained and host page cache can
be bypassed.

Signed-off-by: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20200824105957.61265-1-zhangjiachen.jaycee@bytedance.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
---
 tools/virtiofsd/helper.c         |  4 ++++
 tools/virtiofsd/passthrough_ll.c | 20 ++++++++++++++------
 2 files changed, 18 insertions(+), 6 deletions(-)

Comments

Vivek Goyal Sept. 29, 2020, 9:53 p.m. UTC | #1
On Fri, Sep 25, 2020 at 01:06:55PM +0100, Dr. David Alan Gilbert (git) wrote:
> From: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
> 
> Due to the commit 65da4539803373ec4eec97ffc49ee90083e56efd, the O_DIRECT
> open flag of guest applications will be discarded by virtiofsd. While
> this behavior makes it consistent with the virtio-9p scheme when guest
> applications use direct I/O, we no longer have any chance to bypass the
> host page cache.
> 
> Therefore, we add a flag 'allow_direct_io' to lo_data. If '-o
>  no_allow_direct_io' option is added, or none of '-o allow_direct_io' or
>  '-o no_allow_direct_io' is added, the 'allow_direct_io' will be set to
>  0, and virtiofsd discards O_DIRECT as before. If '-o allow_direct_io'
> is added to the starting command-line, 'allow_direct_io' will be set to
> 1, so that the O_DIRECT flags will be retained and host page cache can
> be bypassed.

Hi Jiachen,

Curious that in what cases you want to bypass host page cache.

Thanks
Vivek

> 
> Signed-off-by: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> Message-Id: <20200824105957.61265-1-zhangjiachen.jaycee@bytedance.com>
> Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
> ---
>  tools/virtiofsd/helper.c         |  4 ++++
>  tools/virtiofsd/passthrough_ll.c | 20 ++++++++++++++------
>  2 files changed, 18 insertions(+), 6 deletions(-)
> 
> diff --git a/tools/virtiofsd/helper.c b/tools/virtiofsd/helper.c
> index 7bc5d7dc5a..85770d63f1 100644
> --- a/tools/virtiofsd/helper.c
> +++ b/tools/virtiofsd/helper.c
> @@ -178,6 +178,10 @@ void fuse_cmdline_help(void)
>             "                               (0 leaves rlimit unchanged)\n"
>             "                               default: min(1000000, fs.file-max - 16384)\n"
>             "                                        if the current rlimit is lower\n"
> +           "    -o allow_direct_io|no_allow_direct_io\n"
> +           "                               retain/discard O_DIRECT flags passed down\n"
> +           "                               to virtiofsd from guest applications.\n"
> +           "                               default: no_allow_direct_io\n"
>             );
>  }
>  
> diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c
> index 784330e0e4..0b229ebd57 100644
> --- a/tools/virtiofsd/passthrough_ll.c
> +++ b/tools/virtiofsd/passthrough_ll.c
> @@ -151,6 +151,7 @@ struct lo_data {
>      int timeout_set;
>      int readdirplus_set;
>      int readdirplus_clear;
> +    int allow_direct_io;
>      struct lo_inode root;
>      GHashTable *inodes; /* protected by lo->mutex */
>      struct lo_map ino_map; /* protected by lo->mutex */
> @@ -179,6 +180,8 @@ static const struct fuse_opt lo_opts[] = {
>      { "cache=always", offsetof(struct lo_data, cache), CACHE_ALWAYS },
>      { "readdirplus", offsetof(struct lo_data, readdirplus_set), 1 },
>      { "no_readdirplus", offsetof(struct lo_data, readdirplus_clear), 1 },
> +    { "allow_direct_io", offsetof(struct lo_data, allow_direct_io), 1 },
> +    { "no_allow_direct_io", offsetof(struct lo_data, allow_direct_io), 0 },
>      FUSE_OPT_END
>  };
>  static bool use_syslog = false;
> @@ -1516,7 +1519,8 @@ static void lo_releasedir(fuse_req_t req, fuse_ino_t ino,
>      fuse_reply_err(req, 0);
>  }
>  
> -static void update_open_flags(int writeback, struct fuse_file_info *fi)
> +static void update_open_flags(int writeback, int allow_direct_io,
> +                              struct fuse_file_info *fi)
>  {
>      /*
>       * With writeback cache, kernel may send read requests even
> @@ -1541,10 +1545,13 @@ static void update_open_flags(int writeback, struct fuse_file_info *fi)
>  
>      /*
>       * O_DIRECT in guest should not necessarily mean bypassing page
> -     * cache on host as well. If somebody needs that behavior, it
> -     * probably should be a configuration knob in daemon.
> +     * cache on host as well. Therefore, we discard it by default
> +     * ('-o no_allow_direct_io'). If somebody needs that behavior,
> +     * the '-o allow_direct_io' option should be set.
>       */
> -    fi->flags &= ~O_DIRECT;
> +    if (!allow_direct_io) {
> +        fi->flags &= ~O_DIRECT;
> +    }
>  }
>  
>  static void lo_create(fuse_req_t req, fuse_ino_t parent, const char *name,
> @@ -1576,7 +1583,7 @@ static void lo_create(fuse_req_t req, fuse_ino_t parent, const char *name,
>          goto out;
>      }
>  
> -    update_open_flags(lo->writeback, fi);
> +    update_open_flags(lo->writeback, lo->allow_direct_io, fi);
>  
>      fd = openat(parent_inode->fd, name, (fi->flags | O_CREAT) & ~O_NOFOLLOW,
>                  mode);
> @@ -1786,7 +1793,7 @@ static void lo_open(fuse_req_t req, fuse_ino_t ino, struct fuse_file_info *fi)
>      fuse_log(FUSE_LOG_DEBUG, "lo_open(ino=%" PRIu64 ", flags=%d)\n", ino,
>               fi->flags);
>  
> -    update_open_flags(lo->writeback, fi);
> +    update_open_flags(lo->writeback, lo->allow_direct_io, fi);
>  
>      sprintf(buf, "%i", lo_fd(req, ino));
>      fd = openat(lo->proc_self_fd, buf, fi->flags & ~O_NOFOLLOW);
> @@ -2823,6 +2830,7 @@ int main(int argc, char *argv[])
>          .debug = 0,
>          .writeback = 0,
>          .posix_lock = 0,
> +        .allow_direct_io = 0,
>          .proc_self_fd = -1,
>      };
>      struct lo_map_elem *root_elem;
> -- 
> 2.26.2
>
Jiachen Zhang Sept. 30, 2020, 2:14 a.m. UTC | #2
On Wed, Sep 30, 2020 at 5:53 AM Vivek Goyal <vgoyal@redhat.com> wrote:

> On Fri, Sep 25, 2020 at 01:06:55PM +0100, Dr. David Alan Gilbert (git)
> wrote:
> > From: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
> >
> > Due to the commit 65da4539803373ec4eec97ffc49ee90083e56efd, the O_DIRECT
> > open flag of guest applications will be discarded by virtiofsd. While
> > this behavior makes it consistent with the virtio-9p scheme when guest
> > applications use direct I/O, we no longer have any chance to bypass the
> > host page cache.
> >
> > Therefore, we add a flag 'allow_direct_io' to lo_data. If '-o
> >  no_allow_direct_io' option is added, or none of '-o allow_direct_io' or
> >  '-o no_allow_direct_io' is added, the 'allow_direct_io' will be set to
> >  0, and virtiofsd discards O_DIRECT as before. If '-o allow_direct_io'
> > is added to the starting command-line, 'allow_direct_io' will be set to
> > 1, so that the O_DIRECT flags will be retained and host page cache can
> > be bypassed.
>
> Hi Jiachen,
>
> Curious that in what cases you want to bypass host page cache.
>
> Thanks
> Vivek
>

Hi Vivek,

Some apps like DBMS may allocate their own file cache in userspace, so they
may want to bypass kernel page cache by using O_DIRECT. When these apps are
running in guest and access virtio-fs files, we'd better obey these needs.
This can also eliminate the host memory usage.

Another case is when we perform file I/O benchmarks on different storage
devices (like HDD and SSD), it's not that fair to introduce ram caches. By
using "cache=none" with "allow_direct_io", we can bypass guest and host page
caches, and access the storage devices directly.

Best wishes,
Jiachen


> >
> > Signed-off-by: Jiachen Zhang <zhangjiachen.jaycee@bytedance.com>
> > Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> > Message-Id: <20200824105957.61265-1-zhangjiachen.jaycee@bytedance.com>
> > Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
> > ---
> >  tools/virtiofsd/helper.c         |  4 ++++
> >  tools/virtiofsd/passthrough_ll.c | 20 ++++++++++++++------
> >  2 files changed, 18 insertions(+), 6 deletions(-)
> >
> > diff --git a/tools/virtiofsd/helper.c b/tools/virtiofsd/helper.c
> > index 7bc5d7dc5a..85770d63f1 100644
> > --- a/tools/virtiofsd/helper.c
> > +++ b/tools/virtiofsd/helper.c
> > @@ -178,6 +178,10 @@ void fuse_cmdline_help(void)
> >             "                               (0 leaves rlimit
> unchanged)\n"
> >             "                               default: min(1000000,
> fs.file-max - 16384)\n"
> >             "                                        if the current
> rlimit is lower\n"
> > +           "    -o allow_direct_io|no_allow_direct_io\n"
> > +           "                               retain/discard O_DIRECT
> flags passed down\n"
> > +           "                               to virtiofsd from guest
> applications.\n"
> > +           "                               default:
> no_allow_direct_io\n"
> >             );
> >  }
> >
> > diff --git a/tools/virtiofsd/passthrough_ll.c
> b/tools/virtiofsd/passthrough_ll.c
> > index 784330e0e4..0b229ebd57 100644
> > --- a/tools/virtiofsd/passthrough_ll.c
> > +++ b/tools/virtiofsd/passthrough_ll.c
> > @@ -151,6 +151,7 @@ struct lo_data {
> >      int timeout_set;
> >      int readdirplus_set;
> >      int readdirplus_clear;
> > +    int allow_direct_io;
> >      struct lo_inode root;
> >      GHashTable *inodes; /* protected by lo->mutex */
> >      struct lo_map ino_map; /* protected by lo->mutex */
> > @@ -179,6 +180,8 @@ static const struct fuse_opt lo_opts[] = {
> >      { "cache=always", offsetof(struct lo_data, cache), CACHE_ALWAYS },
> >      { "readdirplus", offsetof(struct lo_data, readdirplus_set), 1 },
> >      { "no_readdirplus", offsetof(struct lo_data, readdirplus_clear), 1
> },
> > +    { "allow_direct_io", offsetof(struct lo_data, allow_direct_io), 1 },
> > +    { "no_allow_direct_io", offsetof(struct lo_data, allow_direct_io),
> 0 },
> >      FUSE_OPT_END
> >  };
> >  static bool use_syslog = false;
> > @@ -1516,7 +1519,8 @@ static void lo_releasedir(fuse_req_t req,
> fuse_ino_t ino,
> >      fuse_reply_err(req, 0);
> >  }
> >
> > -static void update_open_flags(int writeback, struct fuse_file_info *fi)
> > +static void update_open_flags(int writeback, int allow_direct_io,
> > +                              struct fuse_file_info *fi)
> >  {
> >      /*
> >       * With writeback cache, kernel may send read requests even
> > @@ -1541,10 +1545,13 @@ static void update_open_flags(int writeback,
> struct fuse_file_info *fi)
> >
> >      /*
> >       * O_DIRECT in guest should not necessarily mean bypassing page
> > -     * cache on host as well. If somebody needs that behavior, it
> > -     * probably should be a configuration knob in daemon.
> > +     * cache on host as well. Therefore, we discard it by default
> > +     * ('-o no_allow_direct_io'). If somebody needs that behavior,
> > +     * the '-o allow_direct_io' option should be set.
> >       */
> > -    fi->flags &= ~O_DIRECT;
> > +    if (!allow_direct_io) {
> > +        fi->flags &= ~O_DIRECT;
> > +    }
> >  }
> >
> >  static void lo_create(fuse_req_t req, fuse_ino_t parent, const char
> *name,
> > @@ -1576,7 +1583,7 @@ static void lo_create(fuse_req_t req, fuse_ino_t
> parent, const char *name,
> >          goto out;
> >      }
> >
> > -    update_open_flags(lo->writeback, fi);
> > +    update_open_flags(lo->writeback, lo->allow_direct_io, fi);
> >
> >      fd = openat(parent_inode->fd, name, (fi->flags | O_CREAT) &
> ~O_NOFOLLOW,
> >                  mode);
> > @@ -1786,7 +1793,7 @@ static void lo_open(fuse_req_t req, fuse_ino_t
> ino, struct fuse_file_info *fi)
> >      fuse_log(FUSE_LOG_DEBUG, "lo_open(ino=%" PRIu64 ", flags=%d)\n",
> ino,
> >               fi->flags);
> >
> > -    update_open_flags(lo->writeback, fi);
> > +    update_open_flags(lo->writeback, lo->allow_direct_io, fi);
> >
> >      sprintf(buf, "%i", lo_fd(req, ino));
> >      fd = openat(lo->proc_self_fd, buf, fi->flags & ~O_NOFOLLOW);
> > @@ -2823,6 +2830,7 @@ int main(int argc, char *argv[])
> >          .debug = 0,
> >          .writeback = 0,
> >          .posix_lock = 0,
> > +        .allow_direct_io = 0,
> >          .proc_self_fd = -1,
> >      };
> >      struct lo_map_elem *root_elem;
> > --
> > 2.26.2
> >
>
>
diff mbox series

Patch

diff --git a/tools/virtiofsd/helper.c b/tools/virtiofsd/helper.c
index 7bc5d7dc5a..85770d63f1 100644
--- a/tools/virtiofsd/helper.c
+++ b/tools/virtiofsd/helper.c
@@ -178,6 +178,10 @@  void fuse_cmdline_help(void)
            "                               (0 leaves rlimit unchanged)\n"
            "                               default: min(1000000, fs.file-max - 16384)\n"
            "                                        if the current rlimit is lower\n"
+           "    -o allow_direct_io|no_allow_direct_io\n"
+           "                               retain/discard O_DIRECT flags passed down\n"
+           "                               to virtiofsd from guest applications.\n"
+           "                               default: no_allow_direct_io\n"
            );
 }
 
diff --git a/tools/virtiofsd/passthrough_ll.c b/tools/virtiofsd/passthrough_ll.c
index 784330e0e4..0b229ebd57 100644
--- a/tools/virtiofsd/passthrough_ll.c
+++ b/tools/virtiofsd/passthrough_ll.c
@@ -151,6 +151,7 @@  struct lo_data {
     int timeout_set;
     int readdirplus_set;
     int readdirplus_clear;
+    int allow_direct_io;
     struct lo_inode root;
     GHashTable *inodes; /* protected by lo->mutex */
     struct lo_map ino_map; /* protected by lo->mutex */
@@ -179,6 +180,8 @@  static const struct fuse_opt lo_opts[] = {
     { "cache=always", offsetof(struct lo_data, cache), CACHE_ALWAYS },
     { "readdirplus", offsetof(struct lo_data, readdirplus_set), 1 },
     { "no_readdirplus", offsetof(struct lo_data, readdirplus_clear), 1 },
+    { "allow_direct_io", offsetof(struct lo_data, allow_direct_io), 1 },
+    { "no_allow_direct_io", offsetof(struct lo_data, allow_direct_io), 0 },
     FUSE_OPT_END
 };
 static bool use_syslog = false;
@@ -1516,7 +1519,8 @@  static void lo_releasedir(fuse_req_t req, fuse_ino_t ino,
     fuse_reply_err(req, 0);
 }
 
-static void update_open_flags(int writeback, struct fuse_file_info *fi)
+static void update_open_flags(int writeback, int allow_direct_io,
+                              struct fuse_file_info *fi)
 {
     /*
      * With writeback cache, kernel may send read requests even
@@ -1541,10 +1545,13 @@  static void update_open_flags(int writeback, struct fuse_file_info *fi)
 
     /*
      * O_DIRECT in guest should not necessarily mean bypassing page
-     * cache on host as well. If somebody needs that behavior, it
-     * probably should be a configuration knob in daemon.
+     * cache on host as well. Therefore, we discard it by default
+     * ('-o no_allow_direct_io'). If somebody needs that behavior,
+     * the '-o allow_direct_io' option should be set.
      */
-    fi->flags &= ~O_DIRECT;
+    if (!allow_direct_io) {
+        fi->flags &= ~O_DIRECT;
+    }
 }
 
 static void lo_create(fuse_req_t req, fuse_ino_t parent, const char *name,
@@ -1576,7 +1583,7 @@  static void lo_create(fuse_req_t req, fuse_ino_t parent, const char *name,
         goto out;
     }
 
-    update_open_flags(lo->writeback, fi);
+    update_open_flags(lo->writeback, lo->allow_direct_io, fi);
 
     fd = openat(parent_inode->fd, name, (fi->flags | O_CREAT) & ~O_NOFOLLOW,
                 mode);
@@ -1786,7 +1793,7 @@  static void lo_open(fuse_req_t req, fuse_ino_t ino, struct fuse_file_info *fi)
     fuse_log(FUSE_LOG_DEBUG, "lo_open(ino=%" PRIu64 ", flags=%d)\n", ino,
              fi->flags);
 
-    update_open_flags(lo->writeback, fi);
+    update_open_flags(lo->writeback, lo->allow_direct_io, fi);
 
     sprintf(buf, "%i", lo_fd(req, ino));
     fd = openat(lo->proc_self_fd, buf, fi->flags & ~O_NOFOLLOW);
@@ -2823,6 +2830,7 @@  int main(int argc, char *argv[])
         .debug = 0,
         .writeback = 0,
         .posix_lock = 0,
+        .allow_direct_io = 0,
         .proc_self_fd = -1,
     };
     struct lo_map_elem *root_elem;