An NFS4ERR_RECALLCONFLICT is returned by server from a GET_LAYOUT
only when a Server Sent a RECALL do to that GET_LAYOUT, or
the RECALL and GET_LAYOUT crossed on the wire.
In any way this means we want to wait at most until in-flight IO
is finished and the RECALL can be satisfied.
So a proper wait here is more like 1/10 of a second, not 15 seconds
like we have now. In case of a server bug we delay exponentially
longer on each retry.
Current code totally craps out performance of very large files on
most pnfs-objects layouts, because of how the map changes when the
file has grown into the next raid group.
[Stable: This will patch back to 3.9. If there are earlier still
maintained trees, please tell me I'll send a patch]
CC: Stable Tree <[email protected]>
Signed-off-by: Boaz Harrosh <[email protected]>
---
fs/nfs/nfs4proc.c | 28 +++++++++++++++++++++++++---
1 file changed, 25 insertions(+), 3 deletions(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index d53d678..3ba882c 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7058,7 +7058,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
struct nfs4_state *state = NULL;
unsigned long timeo, giveup;
- dprintk("--> %s\n", __func__);
+ dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
if (!nfs41_sequence_done(task, &lgp->res.seq_res))
goto out;
@@ -7068,10 +7068,32 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
goto out;
case -NFS4ERR_LAYOUTTRYLATER:
case -NFS4ERR_RECALLCONFLICT:
+ /* NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
+ * existing layout before getting a new one).
+ * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
+ * (or clients) writing to the same RAID stripe
+ */
timeo = rpc_get_timeout(task->tk_client);
giveup = lgp->args.timestamp + timeo;
- if (time_after(giveup, jiffies))
- task->tk_status = -NFS4ERR_DELAY;
+ if (time_after(giveup, jiffies)) {
+ unsigned long delay;
+
+ /* Delay for:
+ * - Not less then NFS4_POLL_RETRY_MIN.
+ * - One last time a jiffie before we give up
+ * - exponential backoff (time_now minus start_attempt)
+ */
+ delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
+ min((giveup - jiffies - 1),
+ jiffies - lgp->args.timestamp));
+
+ dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
+ __func__, delay);
+ rpc_delay(task, delay);
+ task->tk_status = 0;
+ rpc_restart_call_prepare(task);
+ goto out; /* Do not call nfs4_async_handle_error() */
+ }
break;
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
--
1.7.11.7
On 01/22/2014 08:34 PM, Boaz Harrosh wrote:
>
> An NFS4ERR_RECALLCONFLICT is returned by server from a GET_LAYOUT
> only when a Server Sent a RECALL do to that GET_LAYOUT, or
> the RECALL and GET_LAYOUT crossed on the wire.
> In any way this means we want to wait at most until in-flight IO
> is finished and the RECALL can be satisfied.
>
> So a proper wait here is more like 1/10 of a second, not 15 seconds
> like we have now. In case of a server bug we delay exponentially
> longer on each retry.
>
> Current code totally craps out performance of very large files on
> most pnfs-objects layouts, because of how the map changes when the
> file has grown into the next raid group.
>
> [Stable: This will patch back to 3.9. If there are earlier still
> maintained trees, please tell me I'll send a patch]
>
> CC: Stable Tree <[email protected]>
> Signed-off-by: Boaz Harrosh <[email protected]>
> ---
> fs/nfs/nfs4proc.c | 28 +++++++++++++++++++++++++---
> 1 file changed, 25 insertions(+), 3 deletions(-)
>
> diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
> index d53d678..3ba882c 100644
> --- a/fs/nfs/nfs4proc.c
> +++ b/fs/nfs/nfs4proc.c
> @@ -7058,7 +7058,7 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
> struct nfs4_state *state = NULL;
> unsigned long timeo, giveup;
>
> - dprintk("--> %s\n", __func__);
> + dprintk("--> %s tk_status => %d\n", __func__, -task->tk_status);
>
> if (!nfs41_sequence_done(task, &lgp->res.seq_res))
> goto out;
> @@ -7068,10 +7068,32 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata)
> goto out;
> case -NFS4ERR_LAYOUTTRYLATER:
> case -NFS4ERR_RECALLCONFLICT:
> + /* NFS4ERR_RECALLCONFLICT is when conflict with self (must recall
> + * existing layout before getting a new one).
> + * NFS4ERR_LAYOUTTRYLATER is a conflict with another client
> + * (or clients) writing to the same RAID stripe
> + */
> timeo = rpc_get_timeout(task->tk_client);
> giveup = lgp->args.timestamp + timeo;
> - if (time_after(giveup, jiffies))
> - task->tk_status = -NFS4ERR_DELAY;
> + if (time_after(giveup, jiffies)) {
> + unsigned long delay;
> +
> + /* Delay for:
> + * - Not less then NFS4_POLL_RETRY_MIN.
> + * - One last time a jiffie before we give up
> + * - exponential backoff (time_now minus start_attempt)
> + */
> + delay = max_t(unsigned long, NFS4_POLL_RETRY_MIN,
> + min((giveup - jiffies - 1),
> + jiffies - lgp->args.timestamp));
> +
> + dprintk("%s: NFS4ERR_RECALLCONFLICT waiting %lu\n",
> + __func__, delay);
Hi Trond. Thanks
I've produced a bug in exofs to ever get stuck in NFS4ERR_RECALLCONFLICT
after the first one. And I see good exponential delay:
Jan 21 11:56:46 fc18-buml18 kernel: nfs4_layoutget_done: NFS4ERR_RECALLCONFLICT waiting 149
Jan 21 11:56:49 fc18-buml18 kernel: nfs4_layoutget_done: NFS4ERR_RECALLCONFLICT waiting 425
Jan 21 11:56:55 fc18-buml18 kernel: nfs4_layoutget_done: NFS4ERR_RECALLCONFLICT waiting 970
Jan 21 11:57:06 fc18-buml18 kernel: nfs4_layoutget_done: NFS4ERR_RECALLCONFLICT waiting 2069
Jan 21 11:57:28 fc18-buml18 kernel: nfs4_layoutget_done: NFS4ERR_RECALLCONFLICT waiting 1713
Now I wish the first one would start at 15 but I see a general delay in all operations on my
setup so for now I blame it on Ganesha and would imagine that nfs4_layoutget_done does not
usually returns after 149 Jiffis.
Is that what you meant?
BTW: Now I have a new problem that when time_after(giveup, jiffies) expires I get an EIO
at dd instead of write through MDS. Investigating ... wish me luck
Thanks
Boaz
> + rpc_delay(task, delay);
> + task->tk_status = 0;
> + rpc_restart_call_prepare(task);
> + goto out; /* Do not call nfs4_async_handle_error() */
> + }
> break;
> case -NFS4ERR_EXPIRED:
> case -NFS4ERR_BAD_STATEID:
>