summaryrefslogtreecommitdiff
path: root/fs/btrfs/async-thread.c
diff options
context:
space:
mode:
authorChris Mason <chris.mason@oracle.com>2008-07-31 23:42:53 +0400
committerChris Mason <chris.mason@oracle.com>2008-09-25 19:04:05 +0400
commit61b4944018449003ac5f9757f4d125dce519cf51 (patch)
tree553855996c641a945344db870b6dfd0d2d02086e /fs/btrfs/async-thread.c
parent37d1aeee3990385e9bb436c50c2f7e120a668df6 (diff)
downloadlinux-61b4944018449003ac5f9757f4d125dce519cf51.tar.xz
Btrfs: Fix streaming read performance with checksumming on
Large streaming reads make for large bios, which means each entry on the list async work queues represents a large amount of data. IO congestion throttling on the device was kicking in before the async worker threads decided a single thread was busy and needed some help. The end result was that a streaming read would result in a single CPU running at 100% instead of balancing the work off to other CPUs. This patch also changes the pre-IO checksum lookup done by reads to work on a per-bio basis instead of a per-page. This results in many extra btree lookups on large streaming reads. Doing the checksum lookup right before bio submit allows us to reuse searches while processing adjacent offsets. Signed-off-by: Chris Mason <chris.mason@oracle.com>
Diffstat (limited to 'fs/btrfs/async-thread.c')
-rw-r--r--fs/btrfs/async-thread.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 5fe6a0d532ed..bc2980c433ef 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -160,7 +160,7 @@ void btrfs_init_workers(struct btrfs_workers *workers, int max)
INIT_LIST_HEAD(&workers->idle_list);
spin_lock_init(&workers->lock);
workers->max_workers = max;
- workers->idle_thresh = 64;
+ workers->idle_thresh = 32;
}
/*