linux/fs/afs
David Howells 100ccd18bb netfs: Optimise away reads above the point at which there can be no data
Track the file position above which the server is not expected to have any
data (the "zero point") and preemptively assume that we can satisfy
requests by filling them with zeroes locally rather than attempting to
download them if they're over that line - even if we've written data back
to the server.  Assume that any data that was written back above that
position is held in the local cache.  Note that we have to split requests
that straddle the line.

Make use of this to optimise away some reads from the server.  We need to
set the zero point in the following circumstances:

 (1) When we see an extant remote inode and have no cache for it, we set
     the zero_point to i_size.

 (2) On local inode creation, we set zero_point to 0.

 (3) On local truncation down, we reduce zero_point to the new i_size if
     the new i_size is lower.

 (4) On local truncation up, we don't change zero_point.

 (5) On local modification, we don't change zero_point.

 (6) On remote invalidation, we set zero_point to the new i_size.

 (7) If stored data is discarded from the pagecache or culled from fscache,
     we must set zero_point above that if the data also got written to the
     server.

 (8) If dirty data is written back to the server, but not fscache, we must
     set zero_point above that.

 (9) If a direct I/O write is made, set zero_point above that.

Assuming the above, any read from the server at or above the zero_point
position will return all zeroes.

The zero_point value can be stored in the cache, provided the above rules
are applied to it by any code that culls part of the local cache.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cachefs@redhat.com
cc: linux-fsdevel@vger.kernel.org
cc: linux-mm@kvack.org
2023-12-28 09:45:27 +00:00
..
addr_list.c afs: Use kfree_rcu() instead of casting kfree() to rcu_callback_t 2020-03-13 10:47:33 -07:00
afs_cm.h treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
afs_fs.h treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152 2019-05-30 11:26:32 -07:00
afs_vl.h afs: Implement client support for the YFSVL.GetCellName RPC op 2020-06-04 15:37:57 +01:00
afs.h rxrpc: Fix timeout of a call that hasn't yet been granted a channel 2023-05-01 07:43:19 +01:00
callback.c netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context 2022-06-09 13:55:00 -07:00
cell.c afs: Fix overwriting of result of DNS query 2023-12-21 09:57:43 -08:00
cmservice.c rxrpc: Tidy up abort generation infrastructure 2023-01-06 09:43:32 +00:00
dir_edit.c afs: fix the afs_dir_get_folio return value 2023-05-06 10:10:08 -07:00
dir_silly.c netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context 2022-06-09 13:55:00 -07:00
dir.c afs: Fix setting of mtime when creating a file/dir/symlink 2023-06-07 09:03:12 -07:00
dynroot.c netfs: Optimise away reads above the point at which there can be no data 2023-12-28 09:45:27 +00:00
file.c netfs: Add iov_iters to (sub)requests to describe various buffers 2023-12-24 15:08:52 +00:00
flock.c fs: remove locks_inode 2023-01-11 06:52:43 -05:00
fs_operation.c netfs: Fix gcc-12 warning by embedding vfs inode in netfs_i_context 2022-06-09 13:55:00 -07:00
fs_probe.c afs: Fix lost servers_outstanding count 2022-12-22 11:40:35 +00:00
fsclient.c afs: Use the operation issue time instead of the reply time for callbacks 2022-09-01 11:44:13 +01:00
inode.c netfs: Optimise away reads above the point at which there can be no data 2023-12-28 09:45:27 +00:00
internal.h afs: Don't use folio->private to record partial modification 2023-12-24 15:08:51 +00:00
Kconfig afs: Convert afs to use the new fscache API 2022-01-07 13:44:47 +00:00
main.c arch: Remove Itanium (IA-64) architecture 2023-09-11 08:13:17 +00:00
Makefile afs: Convert afs to use the new fscache API 2022-01-07 13:44:47 +00:00
misc.c afs: Return -EAGAIN, not -EREMOTEIO, when a file already locked 2022-09-06 21:33:01 -04:00
mntpt.c afs: Remove check of PageError 2022-06-29 08:51:06 -04:00
proc.c afs: Use refcount_t rather than atomic_t 2022-08-02 18:10:11 +01:00
protocol_afs.h afs: Fix corruption in reads at fpos 2G-4G from an OpenAFS server 2021-09-13 09:14:21 +01:00
protocol_uae.h afs: Add support for the UAE error table 2019-06-28 18:37:53 +01:00
protocol_yfs.h afs: Fix corruption in reads at fpos 2G-4G from an OpenAFS server 2021-09-13 09:14:21 +01:00
rotate.c afs: Adjust ACK interpretation to try and cope with NAT 2022-05-22 21:03:02 +01:00
rxrpc.c afs: Fix refcount underflow from error handling race 2023-12-11 15:40:41 -08:00
security.c fs: port ->permission() to pass mnt_idmap 2023-01-19 09:24:28 +01:00
server_list.c afs: Fix afs_server_list to be cleaned up with RCU 2023-11-17 07:55:27 +00:00
server.c afs: Fix server->active leak in afs_put_server 2022-11-30 10:02:37 -08:00
super.c netfs: Move pinning-for-writeback from fscache to netfs 2023-12-24 15:08:49 +00:00
vl_alias.c afs: Add tracing for cell refcount and active user count 2020-10-16 14:39:21 +01:00
vl_list.c afs: Use refcount_t rather than atomic_t 2022-08-02 18:10:11 +01:00
vl_probe.c afs: Fix vlserver probe RTT handling 2023-06-16 14:43:41 -07:00
vl_rotate.c afs: Return ENOENT if no cell DNS record can be found 2023-11-24 14:51:18 +00:00
vlclient.c afs: Fix fall-through warnings for Clang 2021-05-25 07:30:34 -10:00
volume.c afs: Fix use-after-free due to get/remove race in volume tree 2023-12-21 10:16:07 -08:00
write.c afs: Don't use folio->private to record partial modification 2023-12-24 15:08:51 +00:00
xattr.c afs: move afs_xattr_handlers to .rodata 2023-10-09 16:24:16 +02:00
xdr_fs.h afs: Fix directory entry size calculation 2021-01-04 12:25:19 +00:00
yfsclient.c afs: Use the operation issue time instead of the reply time for callbacks 2022-09-01 11:44:13 +01:00