seqid, introduced in NFSv4.0, requires state-changing operations be performed
synchronously, and thus limits parallelism. NFSv4.1 supports "unlimited
parallelism" by using sessions and slots; seqid is no longer used and must be
ignored by NFSv4.1 server. However, the current nfs client always call
nfs_wait_on_seqid() no matter the version is 4.0 or 4.1.
nfs_wait_on_seqid() can be very slow in high-latency network. Using the
Filebench file server workload and the following systemtap script, we measured
the "Seqid_waitqueue" introduced an average 344ms delay in a 10ms-rtt network.
global sleep_count;
global sleep_time;
global sleep_duration;
// called in '__rpc_sleep_on_priority()'
probe kernel.trace("rpc_task_sleep") {
name = kernel_string($q->name);
sleep_time[name, $task] = gettimeofday_us();
}
// called in '__rpc_do_wake_up_task()'
probe kernel.trace("rpc_task_wakeup") {
name = kernel_string($q->name);
now = gettimeofday_us();
old = sleep_time[name, $task];
if (old) {
sleep_count[name] += 1;
sleep_duration[name] += now - old;
delete sleep_time[name, $task];
}
}
probe end {
foreach (name in sleep_count) {
printf("\"%s\" -- sleep count: %d; sleep time: %ld us\n",
name, sleep_count[name],
sleep_duration[name] / sleep_count[name]);
}
}
Systemtap output:
"xprt_pending" -- sleep count: 20051; sleep time: 10453 us
"xprt_sending" -- sleep count: 2489; sleep time: 43 us
"ForeChannel Slot table" -- sleep count: 37; sleep time: 731 us
"Seqid_waitqueue" -- sleep count: 7428; sleep time: 343774 us
This patch avoids the unnecessary nfs_wait_on_seqid() operations for NFSv4.1.
It improves the speed of the Filebench file server workload from 175 ops/sec
to 1550 ops/sec.
This patch is based on 3.18-rc3, and has been tested in 3.14.17 and 3.18-rc3.
Signed-off-by: Ming Chen <mchen@xxxxxxxxxxxxxxxxx>
---
fs/nfs/nfs4proc.c | 15 ++++++++++-----
1 file changed, 10 insertions(+), 5 deletions(-)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 405bd95..be06010 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1778,7 +1778,8 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
struct nfs4_state_owner *sp = data->owner;
struct nfs_client *clp = sp->so_server->nfs_client;
- if (nfs_wait_on_sequence(data->o_arg.seqid, task) != 0)
+ if (!nfs4_get_session(sp->so_server) &&
+ nfs_wait_on_sequence(data->o_arg.seqid, task) != 0)
goto out_wait;
/*
* Check if we still need to send an OPEN call, or if we can use
@@ -2617,7 +2618,8 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
int call_close = 0;
dprintk("%s: begin!\n", __func__);
- if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
+ if (!nfs4_get_session(state->owner->so_server) &&
+ nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
goto out_wait;
task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
@@ -5399,7 +5401,8 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
{
struct nfs4_unlockdata *calldata = data;
- if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
+ if (!nfs4_get_session(calldata->server) &&
+ nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
goto out_wait;
if (test_bit(NFS_LOCK_INITIALIZED, &calldata->lsp->ls_flags) == 0) {
/* Note: exit _without_ running nfs4_locku_done */
@@ -5566,11 +5569,13 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
struct nfs4_state *state = data->lsp->ls_state;
dprintk("%s: begin!\n", __func__);
- if (nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0)
+ if (!nfs4_get_session(data->server) &&
+ nfs_wait_on_sequence(data->arg.lock_seqid, task) != 0)
goto out_wait;
/* Do we need to do an open_to_lock_owner? */
if (!(data->arg.lock_seqid->sequence->flags & NFS_SEQID_CONFIRMED)) {
- if (nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) {
+ if (!nfs4_get_session(data->server) &&
+ nfs_wait_on_sequence(data->arg.open_seqid, task) != 0) {
goto out_release_lock_seqid;
}
data->arg.open_stateid = &state->open_stateid;
--
1.8.1.2
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
