This patch sets the io_pages bdi hint based on the rvsize mount option.
Without this patch large buffered reads (request size > max readahead)
are processed sequentially in chunks of the readahead size (i.e. read
requests are sent out up to the readahead size, then the
do_generic_file_read() function waits until the first page is received).
With this patch read requests are sent out up to the size specified in
the new rvsize mount option at once (default: 64 MB).
Signed-off-by: Andreas Gerstmayr <andreas.gerstmayr@xxxxxxxxxxxx>
---
Thanks for your review.
On second thought, I think I should not reuse the rsize mount option
(maximum read size per OSD request), therefore I created a new mount
option rvsize with a default value of 64 MB (as you suggested).
(Note: This patch depends on kernel version 4.10-rc1)
Documentation/filesystems/ceph.txt | 4 ++++
fs/ceph/super.c | 15 +++++++++++++++
fs/ceph/super.h | 8 +++++---
3 files changed, 24 insertions(+), 3 deletions(-)
diff --git a/Documentation/filesystems/ceph.txt b/Documentation/filesystems/ceph.txt
index f5306ee..65171e1 100644
--- a/Documentation/filesystems/ceph.txt
+++ b/Documentation/filesystems/ceph.txt
@@ -104,6 +104,10 @@ Mount Options
rasize=X
Specify the maximum readahead.
+ rvsize=X
+ Specify the maximum volume of read requests sent out at once.
+ The default is 64 MB.
+
mount_timeout=X
Specify the timeout value for mount (in seconds), in the case
of a non-responsive Ceph file system. The default is 30
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 6bd20d7..71bed5a 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -111,6 +111,7 @@ enum {
Opt_wsize,
Opt_rsize,
Opt_rasize,
+ Opt_rvsize,
Opt_caps_wanted_delay_min,
Opt_caps_wanted_delay_max,
Opt_cap_release_safety,
@@ -149,6 +150,7 @@ enum {
{Opt_wsize, "wsize=%d"},
{Opt_rsize, "rsize=%d"},
{Opt_rasize, "rasize=%d"},
+ {Opt_rvsize, "rvsize=%d"},
{Opt_caps_wanted_delay_min, "caps_wanted_delay_min=%d"},
{Opt_caps_wanted_delay_max, "caps_wanted_delay_max=%d"},
{Opt_cap_release_safety, "cap_release_safety=%d"},
@@ -233,6 +235,9 @@ static int parse_fsopt_token(char *c, void *private)
case Opt_rasize:
fsopt->rasize = intval;
break;
+ case Opt_rvsize:
+ fsopt->rvsize = intval;
+ break;
case Opt_caps_wanted_delay_min:
fsopt->caps_wanted_delay_min = intval;
break;
@@ -381,6 +386,7 @@ static int parse_mount_options(struct ceph_mount_options **pfsopt,
fsopt->rsize = CEPH_RSIZE_DEFAULT;
fsopt->rasize = CEPH_RASIZE_DEFAULT;
+ fsopt->rvsize = CEPH_RVSIZE_DEFAULT;
fsopt->snapdir_name = kstrdup(CEPH_SNAPDIRNAME_DEFAULT, GFP_KERNEL);
if (!fsopt->snapdir_name) {
err = -ENOMEM;
@@ -495,6 +501,8 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_printf(m, ",rsize=%d", fsopt->rsize);
if (fsopt->rasize != CEPH_RASIZE_DEFAULT)
seq_printf(m, ",rasize=%d", fsopt->rasize);
+ if (fsopt->rvsize != CEPH_RVSIZE_DEFAULT)
+ seq_printf(m, ",rvsize=%d", fsopt->rvsize);
if (fsopt->congestion_kb != default_congestion_kb())
seq_printf(m, ",write_congestion_kb=%d", fsopt->congestion_kb);
if (fsopt->caps_wanted_delay_min != CEPH_CAPS_WANTED_DELAY_MIN_DEFAULT)
@@ -952,6 +960,13 @@ static int ceph_register_bdi(struct super_block *sb,
fsc->backing_dev_info.ra_pages =
VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+ if (fsc->mount_options->rvsize)
+ fsc->backing_dev_info.io_pages =
+ (fsc->mount_options->rvsize + PAGE_SIZE - 1)
+ >> PAGE_SHIFT;
+ else
+ fsc->backing_dev_info.io_pages = ULONG_MAX;
+
err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
atomic_long_inc_return(&bdi_seq));
if (!err)
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3373b61..676ef6d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -45,8 +45,9 @@
#define ceph_test_mount_opt(fsc, opt) \
(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
-#define CEPH_RSIZE_DEFAULT 0 /* max read size */
-#define CEPH_RASIZE_DEFAULT (8192*1024) /* readahead */
+#define CEPH_RSIZE_DEFAULT 0 /* max read size per osd request */
+#define CEPH_RASIZE_DEFAULT (8192*1024) /* max readahead */
+#define CEPH_RVSIZE_DEFAULT (64*1024*1024) /* max volume of read requests sent out at once */
#define CEPH_MAX_READDIR_DEFAULT 1024
#define CEPH_MAX_READDIR_BYTES_DEFAULT (512*1024)
#define CEPH_SNAPDIRNAME_DEFAULT ".snap"
@@ -56,8 +57,9 @@ struct ceph_mount_options {
int sb_flags;
int wsize; /* max write size */
- int rsize; /* max read size */
+ int rsize; /* max read size per osd request */
int rasize; /* max readahead */
+ int rvsize; /* max volume of read requests sent out at once */
int congestion_kb; /* max writeback in flight */
int caps_wanted_delay_min, caps_wanted_delay_max;
int cap_release_safety;
--
1.8.3.1
--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
