NFS: Don't clear desc->pg_moreio in nfs_do_recoalesce()
Recoalescing does not affect whether or not we've already sent off I/O, and doing so means that we end up sending a bunch of synchronous for cases where we actually need to be using unstable writes. Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
This commit is contained in:
parent
03d5eb65b5
commit
d4c30454db
|
@ -1100,8 +1100,6 @@ static int nfs_do_recoalesce(struct nfs_pageio_descriptor *desc)
|
||||||
mirror->pg_base = 0;
|
mirror->pg_base = 0;
|
||||||
mirror->pg_recoalesce = 0;
|
mirror->pg_recoalesce = 0;
|
||||||
|
|
||||||
desc->pg_moreio = 0;
|
|
||||||
|
|
||||||
while (!list_empty(&head)) {
|
while (!list_empty(&head)) {
|
||||||
struct nfs_page *req;
|
struct nfs_page *req;
|
||||||
|
|
||||||
|
|
Loading…
Reference in New Issue