d/freebsd-skq
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add a sysctl vfs.read_min to complement the exiting vfs.read_max. It

Browse Source 
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
This commit is contained in:
Scott Long 2013-05-07 08:16:21 +00:00
parent 7dcb2bea01
commit ab8f55b9fd
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
sys/kern/vfs_cluster.c
View File

@ -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;
@ -166,12 +170,20 @@ cluster_read(struct vnode *vp, u_quad_t filesize, daddr_t lblkno, long size,
} else {
off_t firstread = bp->b_offset;
int nblks;
long minread;
KASSERT(bp->b_offset != NOOFFSET,
("cluster_read: no buffer offset"));
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.