Merge pull request #1321 from trapexit/allowmmap

Add support for 'direct-io-allow-mmap' if supported by kernel

README.md

@@ -91,6 +91,11 @@ start with one of the following option sets.
 
 `cache.files=auto-full,dropcacheonclose=true,category.create=mfs`
 
+or if you are on a Linux kernel >= 6.6.x mergerfs will enable a mode
+that allows shared mmap when `cache.files=off`. To be sure of the best
+performance between `cache.files=off` and `cache.files=auto-full`
+you'll need to do your own benchmarking but often `off` is faster.
+
 #### You don't need `mmap`
 
 `cache.files=off,dropcacheonclose=true,category.create=mfs`
@@ -162,6 +167,11 @@ These options are the same regardless of whether you use them with the
  longer need the data and it can drop its cache. Recommended when
  **cache.files=partial|full|auto-full|per-process** to limit double
  caching. (default: false)
+* **direct-io-allow-mmap=BOOL**: On newer kernels (>= 6.6) it is
+ possible to disable file page caching while still allowing for
+ shared mmap support. mergerfs will enable this feature if available
+ but an option is provided to turn it off for testing and debugging
+ purposes. (default: true)
 * **symlinkify=BOOL**: When enabled and a file is not writable and its
  mtime or ctime is older than **symlinkify_timeout** files will be
  reported as symlinks to the original files. Please read more below

libfuse/include/fuse_common.h

@@ -108,23 +108,26 @@ struct fuse_file_info_t
  * FUSE_CAP_IOCTL_DIR: ioctl support on directories
  * FUSE_CAP_CACHE_SYMLINKS: cache READLINK responses
  */
-#define FUSE_CAP_ASYNC_READ (1 << 0)
-#define FUSE_CAP_POSIX_LOCKS (1 << 1)
-#define FUSE_CAP_ATOMIC_O_TRUNC (1 << 3)
-#define FUSE_CAP_EXPORT_SUPPORT (1 << 4)
-#define FUSE_CAP_BIG_WRITES (1 << 5)
-#define FUSE_CAP_DONT_MASK (1 << 6)
-#define FUSE_CAP_FLOCK_LOCKS (1 << 10)
-#define FUSE_CAP_IOCTL_DIR (1 << 11)
-#define FUSE_CAP_READDIR_PLUS (1 << 13)
-#define FUSE_CAP_READDIR_PLUS_AUTO (1 << 14)
-#define FUSE_CAP_ASYNC_DIO (1 << 15)
-#define FUSE_CAP_WRITEBACK_CACHE (1 << 16)
-#define FUSE_CAP_PARALLEL_DIROPS (1 << 18)
-#define FUSE_CAP_POSIX_ACL (1 << 19)
-#define FUSE_CAP_CACHE_SYMLINKS (1 << 20)
-#define FUSE_CAP_MAX_PAGES (1 << 21)
-#define FUSE_CAP_SETXATTR_EXT (1 << 22)
+#define FUSE_CAP_ASYNC_READ (1ULL << 0)
+#define FUSE_CAP_POSIX_LOCKS (1ULL << 1)
+#define FUSE_CAP_ATOMIC_O_TRUNC (1ULL << 3)
+#define FUSE_CAP_EXPORT_SUPPORT (1ULL << 4)
+#define FUSE_CAP_BIG_WRITES (1ULL << 5)
+#define FUSE_CAP_DONT_MASK (1ULL << 6)
+#define FUSE_CAP_FLOCK_LOCKS (1ULL << 10)
+#define FUSE_CAP_IOCTL_DIR (1ULL << 11)
+#define FUSE_CAP_READDIR_PLUS (1ULL << 13)
+#define FUSE_CAP_READDIR_PLUS_AUTO (1ULL << 14)
+#define FUSE_CAP_ASYNC_DIO (1ULL << 15)
+#define FUSE_CAP_WRITEBACK_CACHE (1ULL << 16)
+#define FUSE_CAP_PARALLEL_DIROPS (1ULL << 18)
+#define FUSE_CAP_POSIX_ACL (1ULL << 19)
+#define FUSE_CAP_CACHE_SYMLINKS (1ULL << 20)
+#define FUSE_CAP_MAX_PAGES (1ULL << 21)
+#define FUSE_CAP_SETXATTR_EXT (1ULL << 22)
+#define FUSE_CAP_DIRECT_IO_ALLOW_MMAP (1ULL << 23)
+#define FUSE_CAP_CREATE_SUPP_GROUP (1ULL << 24)
+
 
 /**
  * Ioctl flags
@@ -150,56 +153,17 @@ struct fuse_file_info_t
  * indicate the value requested by the filesystem. The requested
  * value must usually be smaller than the indicated value.
  */
-struct fuse_conn_info {
- /**
- * Major version of the protocol (read-only)
- */
+struct fuse_conn_info
+{
  unsigned proto_major;
-
- /**
- * Minor version of the protocol (read-only)
- */
  unsigned proto_minor;
-
- /**
- * Maximum size of the write buffer
- */
  unsigned max_write;
-
- /**
- * Maximum readahead
- */
  unsigned max_readahead;
-
- /**
- * Capability flags, that the kernel supports
- */
- unsigned capable;
-
- /**
- * Capability flags, that the filesystem wants to enable
- */
- unsigned want;
-
- /**
- * Maximum number of backgrounded requests
- */
+ uint64_t capable;
+ uint64_t want;
  unsigned max_background;
-
- /**
- * Kernel congestion threshold parameter
- */
  unsigned congestion_threshold;
-
- /**
- * Max pages
- */
  uint16_t max_pages;
-
- /**
- * For future use.
- */
- unsigned reserved[22];
 };
 
 struct fuse_session;

libfuse/lib/debug.c

@@ -158,9 +158,9 @@ open_flag_to_str(const uint64_t offset_)
 static
 const
 char*
-fuse_flag_to_str(const uint32_t offset_)
+fuse_flag_to_str(const uint64_t offset_)
 {
- switch(1 << offset_)
+ switch(1ULL << offset_)
  {
  FUSE_INIT_FLAG_CASE(ASYNC_READ);
  FUSE_INIT_FLAG_CASE(POSIX_LOCKS);
@@ -189,6 +189,16 @@ fuse_flag_to_str(const uint32_t offset_)
  FUSE_INIT_FLAG_CASE(NO_OPENDIR_SUPPORT);
  FUSE_INIT_FLAG_CASE(EXPLICIT_INVAL_DATA);
  FUSE_INIT_FLAG_CASE(MAP_ALIGNMENT);
+ FUSE_INIT_FLAG_CASE(SUBMOUNTS);
+ FUSE_INIT_FLAG_CASE(HANDLE_KILLPRIV_V2);
+ FUSE_INIT_FLAG_CASE(SETXATTR_EXT);
+ FUSE_INIT_FLAG_CASE(INIT_EXT);
+ FUSE_INIT_FLAG_CASE(INIT_RESERVED);
+ FUSE_INIT_FLAG_CASE(SECURITY_CTX);
+ FUSE_INIT_FLAG_CASE(HAS_INODE_DAX);
+ FUSE_INIT_FLAG_CASE(CREATE_SUPP_GROUP);
+ FUSE_INIT_FLAG_CASE(HAS_EXPIRE_ONLY);
+ FUSE_INIT_FLAG_CASE(DIRECT_IO_ALLOW_MMAP);
  }
 
  return NULL;
@@ -200,7 +210,7 @@ static
 void
 debug_open_flags(const uint32_t flags_)
 {
- fprintf(stderr,"%s,",open_accmode_to_str(flags_));
+ fprintf(stderr,"%s, ",open_accmode_to_str(flags_));
  for(int i = 0; i < (sizeof(flags_) * 8); i++)
  {
  const char *str;
@@ -212,7 +222,7 @@ debug_open_flags(const uint32_t flags_)
  if(str == NULL)
  continue;
 
- fprintf(stderr,"%s,",str);
+ fprintf(stderr,"%s, ",str);
  }
 }
 
@@ -717,28 +727,31 @@ debug_fuse_fallocate_in(const void *arg_)
 void
 debug_fuse_init_in(const struct fuse_init_in *arg_)
 {
+ uint64_t flags;
+
+ flags = (((uint64_t)arg_->flags) | ((uint64_t)arg_->flags2) << 32);
  fprintf(g_OUTPUT,
  "FUSE_INIT_IN: "
  " major=%u;"
  " minor=%u;"
  " max_readahead=%u;"
- " flags=0x%08X (",
+ " flags=0x%016lx (",
  arg_->major,
  arg_->minor,
  arg_->max_readahead,
- arg_->flags);
- for(uint64_t i = 0; i < (sizeof(arg_->flags)*8); i++)
+ flags);
+ for(uint64_t i = 0; i < (sizeof(flags)*8); i++)
  {
  const char *str;
 
- if(!(arg_->flags & (1ULL << i)))
+ if(!(flags & (1ULL << i)))
  continue;
 
  str = fuse_flag_to_str(i);
  if(str == NULL)
  continue;
 
- fprintf(g_OUTPUT,"%s,",str);
+ fprintf(g_OUTPUT,"%s, ",str);
  }
  fprintf(g_OUTPUT,")\n");
 }
@@ -748,7 +761,10 @@ debug_fuse_init_out(const uint64_t unique_,
  const struct fuse_init_out *arg_,
  const uint64_t argsize_)
 {
+ uint64_t flags;
  const struct fuse_init_out *arg = arg_;
+
+ flags = (((uint64_t)arg->flags) | ((uint64_t)arg->flags2) << 32);
  fprintf(g_OUTPUT,
  /* "unique=0x%016"PRIx64";" */
  /* " opcode=RESPONSE;" */
@@ -758,27 +774,27 @@ debug_fuse_init_out(const uint64_t unique_,
  " major=%u;"
  " minor=%u;"
  " max_readahead=%u;"
- " flags=0x%08X ("
+ " flags=0x%016lx ("
  ,
  /* unique_, */
  /* sizeof(struct fuse_out_header) + argsize_, */
  arg->major,
  arg->minor,
  arg->max_readahead,
- arg->flags);
+ flags);
 
- for(uint64_t i = 0; i < (sizeof(arg->flags)*8); i++)
+ for(uint64_t i = 0; i < (sizeof(flags)*8); i++)
  {
  const char *str;
 
- if(!(arg->flags & (1ULL << i)))
+ if(!(flags & (1ULL << i)))
  continue;
 
  str = fuse_flag_to_str(i);
  if(str == NULL)
  continue;
 
- fprintf(g_OUTPUT,"%s,",str);
+ fprintf(g_OUTPUT,"%s, ",str);
  }
 
  fprintf(g_OUTPUT,