Skip to contentSkip to conversation

RFC/Patch: Make NFS Readahead tunable

PATCH Martin Knoblauch 2 participants 2 messages Apr 15, 2008 1 message not in the archive

Subsystems (2)
NFS client NFS server
lore
Share & tools
lore

Martin Knoblauch

author
#0 lore raw

Hi,

while tracking down a very interesting interaction between Sun/SAM-FS and Linux NFS clients, we found out that the value of NFS_MAX_READ_AHEAD is to agressive/big for the specific use-case.

For testing, instead of always recompiling the kernel with different values, I came up with the following patch. It introduces a tunable "/proc/sys/fs/nfs/nfs_ra_factor" with possible values between 0-15.

Not sure whether it is actually a good thing to have. Better would be to set the read-ahead factor per filesystem via a mount option.

The patch is against 2.6.24. It applies with offsets against 2.6.25-rc9. In case my mail client messes up the whitespace, the patch is also attached.

Signed-off-by Martin Knoblauch <[email protected]>
fs/nfs/client.c 2008-04-14 16:44:22.000000000 +0200 renamed from fs/nfs/client.c 2008-01-24 23:58:37.000000000 +0100 +10 -1
diff -ru linux-2.6.24-orig/fs/nfs/client.c linux-2.6.24-nfs_ra/fs/nfs/client.c
@@ -601,6 +601,11 @@
 }
 
 /*
+ * NFS Client Read-Ahead factor
+*/
+unsigned int nfs_ra_factor;
+
+/*
  * Load up the server record from information gained in an fsinfo record
  */
 static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo)

@@ -625,7 +630,9 @@
                server->rsize = NFS_MAX_FILE_IO_SIZE;
        server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
-       server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
+       printk(KERN_INFO "nfs_server_set_fsinfo: rsize, wsize, rpages, nfs_ra_factor, ra_pages: %d %d %d %d %d\n",
+               server->rsize,server->wsize,server->rpages,nfs_ra_factor,server->rpages * nfs_ra_factor);
+       server->backing_dev_info.ra_pages = server->rpages * nfs_ra_factor;
 
        if (server->wsize > max_rpc_payload)
                server->wsize = max_rpc_payload;

@@ -1359,6 +1366,8 @@
 {
        struct proc_dir_entry *p;
 
+       nfs_ra_factor = NFS_MAX_READAHEAD;
+
        proc_fs_nfs = proc_mkdir("nfsfs", proc_root_fs);
        if (!proc_fs_nfs)
                goto error_0;
fs/nfs/sysctl.c 2008-04-14 16:15:03.000000000 +0200 renamed from fs/nfs/sysctl.c 2008-01-24 23:58:37.000000000 +0100 +13 -0
diff -ru linux-2.6.24-orig/fs/nfs/sysctl.c linux-2.6.24-nfs_ra/fs/nfs/sysctl.c
@@ -14,9 +14,12 @@
 #include <linux/nfs_fs.h>
 
 #include "callback.h"
+#include "internal.h"
 
 static const int nfs_set_port_min = 0;
 static const int nfs_set_port_max = 65535;
+static const unsigned int min_nfs_ra_factor = 0;
+static const unsigned int max_nfs_ra_factor = NFS_MAX_READAHEAD;
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
 static ctl_table nfs_cb_sysctls[] = {

@@ -58,6 +61,16 @@
                .mode           = 0644,
                .proc_handler   = &proc_dointvec,
        },
+       {
+               .ctl_name = CTL_UNNUMBERED,
+               .procname = "nfs_ra_factor",
+               .data = &nfs_ra_factor,
+               .maxlen = sizeof(unsigned int),
+               .mode = 0644,
+               .proc_handler = &proc_dointvec_minmax,
+               .extra1 = (unsigned int *)&min_nfs_ra_factor,
+               .extra2 = (unsigned int *)&max_nfs_ra_factor,
+       },
        { .ctl_name = 0 }
 };
include/linux/nfs_fs.h 2008-04-14 15:58:57.000000000 +0200 renamed from include/linux/nfs_fs.h 2008-01-24 23:58:37.000000000 +0100 +5 -0
diff -ru linux-2.6.24-orig/include/linux/nfs_fs.h linux-2.6.24-nfs_ra/include/linux/nfs_fs.h
@@ -415,6 +415,11 @@
 extern void nfs_writedata_release(void *);
 
 /*
+ * linux/fs/nfs/client.c
+*/
+extern unsigned int nfs_ra_factor;
+
+/*
  * Try to write back everything synchronously (but check the
  * return value!)
  */

Cheers
Martin
------------------------------------------------------
Martin Knoblauch

email: k n o b i AT knobisoft DOT de
www:   http://www.knobisoft.de
fs/nfs/client.c +10 -1
diff -ru linux-2.6.24-orig/fs/nfs/client.c linux-2.6.24-nfs_ra/fs/nfs/client.c
@@ -601,6 +601,11 @@
 }
 
 /*
+ * NFS Client Read-Ahead factor
+*/
+unsigned int nfs_ra_factor;
+
+/*
  * Load up the server record from information gained in an fsinfo record
  */
 static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo *fsinfo)

@@ -625,7 +630,9 @@
 		server->rsize = NFS_MAX_FILE_IO_SIZE;
 	server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 
-	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
+	printk(KERN_INFO "nfs_server_set_fsinfo: rsize, wsize, rpages, nfs_ra_factor, ra_pages: %d %d %d %d %d\n",
+		server->rsize,server->wsize,server->rpages,nfs_ra_factor,server->rpages * nfs_ra_factor);
+	server->backing_dev_info.ra_pages = server->rpages * nfs_ra_factor;
 
 	if (server->wsize > max_rpc_payload)
 		server->wsize = max_rpc_payload;

@@ -1359,6 +1366,8 @@
 {
 	struct proc_dir_entry *p;
 
+	nfs_ra_factor = NFS_MAX_READAHEAD;
+
 	proc_fs_nfs = proc_mkdir("nfsfs", proc_root_fs);
 	if (!proc_fs_nfs)
 		goto error_0;
fs/nfs/sysctl.c +13 -0
diff -ru linux-2.6.24-orig/fs/nfs/sysctl.c linux-2.6.24-nfs_ra/fs/nfs/sysctl.c
@@ -14,9 +14,12 @@
 #include <linux/nfs_fs.h>
 
 #include "callback.h"
+#include "internal.h"
 
 static const int nfs_set_port_min = 0;
 static const int nfs_set_port_max = 65535;
+static const unsigned int min_nfs_ra_factor = 0;
+static const unsigned int max_nfs_ra_factor = NFS_MAX_READAHEAD;
 static struct ctl_table_header *nfs_callback_sysctl_table;
 
 static ctl_table nfs_cb_sysctls[] = {

@@ -58,6 +61,16 @@
 		.mode		= 0644,
 		.proc_handler	= &proc_dointvec,
 	},
+	{
+		.ctl_name = CTL_UNNUMBERED,
+		.procname = "nfs_ra_factor",
+		.data = &nfs_ra_factor,
+		.maxlen = sizeof(unsigned int),
+		.mode = 0644,
+		.proc_handler = &proc_dointvec_minmax,
+		.extra1 = (unsigned int *)&min_nfs_ra_factor,
+		.extra2 = (unsigned int *)&max_nfs_ra_factor,
+	},
 	{ .ctl_name = 0 }
 };
include/linux/nfs_fs.h +5 -0
diff -ru linux-2.6.24-orig/include/linux/nfs_fs.h linux-2.6.24-nfs_ra/include/linux/nfs_fs.h
@@ -415,6 +415,11 @@
 extern void nfs_writedata_release(void *);
 
 /*
+ * linux/fs/nfs/client.c
+*/
+extern unsigned int nfs_ra_factor;
+
+/*
  * Try to write back everything synchronously (but check the
  * return value!)
  */

A message that is not in the archive (sent off-list or not yet received): 975253.58176.qm-f6uctMgKLEavuULXzWHTWIglqE1Y4D90QQ4Iyu8u01E@public.gmane.org

#2 lore raw
Quoted 9 lines · Martin Knoblauch

Hi,

while tracking down a very interesting interaction between Sun/SAM-FS and Linux NFS clients, we found out that the value of NFS_MAX_READ_AHEAD is to agressive/big for the specific use-case.

For testing, instead of always recompiling the kernel with different values, I came up with the following patch. It introduces a tunable "/proc/sys/fs/nfs/nfs_ra_factor" with possible values between 0-15.

Not sure whether it is actually a good thing to have. Better would be to set the read-ahead factor per filesystem via a mount option.

The patch is against 2.6.24. It applies with offsets against 2.6.25-rc9. In case my mail client messes up the whitespace, the patch is also attached.

NFS_MAX_READ_AHEAD just sets an upper limit on the standard vfs/mm-level page readahead algorithm. If you need finer control over that readahead algorithm, then the kernel already has full support for the posix_fadvise() system call.

Cheers
Trond