svn commit: r250327 - head/sys/kern
Scott Long
scottl at FreeBSD.org
Tue May 7 08:16:22 UTC 2013
Author: scottl
Date: Tue May 7 08:16:21 2013
New Revision: 250327
URL: http://svnweb.freebsd.org/changeset/base/250327
Log:
Add a sysctl vfs.read_min to complement the exiting vfs.read_max. It
defaults to 1, meaning that it's off.
When read-ahead is enabled on a file, the vfs cluster code deliberately
breaks a read into 2 I/O transactions; one to satisfy the actual read,
and one to perform read-ahead. This makes sense in low-latency
circumstances, but often produces unbalanced i/o transactions that
penalize disks. By setting vfs.read_min, we can tell the algorithm to
fetch a larger transaction that what we asked for, achieving the same
effect as the read-ahead but without the doubled, unbalanced transaction
and the slightly lower latency. This significantly helps our workloads
with video streaming.
Submitted by: emax
Reviewed by: kib
Obtained from: Netflix
Modified:
head/sys/kern/vfs_cluster.c
Modified: head/sys/kern/vfs_cluster.c
==============================================================================
--- head/sys/kern/vfs_cluster.c Tue May 7 07:52:18 2013 (r250326)
+++ head/sys/kern/vfs_cluster.c Tue May 7 08:16:21 2013 (r250327)
@@ -76,6 +76,10 @@ static int read_max = 64;
SYSCTL_INT(_vfs, OID_AUTO, read_max, CTLFLAG_RW, &read_max, 0,
"Cluster read-ahead max block count");
+static int read_min = 1;
+SYSCTL_INT(_vfs, OID_AUTO, read_min, CTLFLAG_RW, &read_min, 0,
+ "Cluster read min block count");
+
/* Page expended to mark partially backed buffers */
extern vm_page_t bogus_page;
@@ -166,6 +170,7 @@ cluster_read(struct vnode *vp, u_quad_t
} else {
off_t firstread = bp->b_offset;
int nblks;
+ long minread;
KASSERT(bp->b_offset != NOOFFSET,
("cluster_read: no buffer offset"));
@@ -173,6 +178,13 @@ cluster_read(struct vnode *vp, u_quad_t
ncontig = 0;
/*
+ * Adjust totread if needed
+ */
+ minread = read_min * size;
+ if (minread > totread)
+ totread = minread;
+
+ /*
* Compute the total number of blocks that we should read
* synchronously.
*/
More information about the svn-src-all
mailing list