aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ceph
diff options
context:
space:
mode:
authorSage Weil <sage@inktank.com>2012-11-28 12:28:24 -0800
committerAlex Elder <elder@inktank.com>2012-12-13 08:13:06 -0600
commit83aff95eb9d60aff5497e9f44a2ae906b86d8e88 (patch)
treeb191a3640990e4b7cc13b2db423449b90086f71b /fs/ceph
parentcfc84c9f73ab8a6933bd4f36efac1196cddad581 (diff)
libceph: remove 'osdtimeout' option
This would reset a connection with any OSD that had an outstanding request that was taking more than N seconds. The idea was that if the OSD was buggy, the client could compensate by resending the request. In reality, this only served to hide server bugs, and we haven't actually seen such a bug in quite a while. Moreover, the userspace client code never did this. More importantly, often the request is taking a long time because the OSD is trying to recover, or overloaded, and killing the connection and retrying would only make the situation worse by giving the OSD more work to do. Signed-off-by: Sage Weil <sage@inktank.com> Reviewed-by: Alex Elder <elder@inktank.com>
Diffstat (limited to 'fs/ceph')
-rw-r--r--fs/ceph/super.c2
1 files changed, 0 insertions, 2 deletions
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2f586b0e5e0..fcda1c73a1e 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -403,8 +403,6 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
seq_printf(m, ",mount_timeout=%d", opt->mount_timeout);
if (opt->osd_idle_ttl != CEPH_OSD_IDLE_TTL_DEFAULT)
seq_printf(m, ",osd_idle_ttl=%d", opt->osd_idle_ttl);
- if (opt->osd_timeout != CEPH_OSD_TIMEOUT_DEFAULT)
- seq_printf(m, ",osdtimeout=%d", opt->osd_timeout);
if (opt->osd_keepalive_timeout != CEPH_OSD_KEEPALIVE_DEFAULT)
seq_printf(m, ",osdkeepalivetimeout=%d",
opt->osd_keepalive_timeout);