linux_dsm_epyc7002/net/sunrpc/stats.c

337 lines
8.3 KiB
C
Raw Normal View History

/*
* linux/net/sunrpc/stats.c
*
* procfs-based user access to generic RPC statistics. The stats files
* reside in /proc/net/rpc.
*
* The read routines assume that the buffer passed in is just big enough.
* If you implement an RPC service that has its own stats routine which
* appends the generic RPC stats, make sure you don't exceed the PAGE_SIZE
* limit.
*
* Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
*/
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sunrpc/clnt.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/sunrpc/metrics.h>
#include <linux/rcupdate.h>
#include <trace/events/sunrpc.h>
#include "netns.h"
#define RPCDBG_FACILITY RPCDBG_MISC
/*
* Get RPC client stats
*/
static int rpc_proc_show(struct seq_file *seq, void *v) {
const struct rpc_stat *statp = seq->private;
const struct rpc_program *prog = statp->program;
unsigned int i, j;
seq_printf(seq,
"net %u %u %u %u\n",
statp->netcnt,
statp->netudpcnt,
statp->nettcpcnt,
statp->nettcpconn);
seq_printf(seq,
"rpc %u %u %u\n",
statp->rpccnt,
statp->rpcretrans,
statp->rpcauthrefresh);
for (i = 0; i < prog->nrvers; i++) {
const struct rpc_version *vers = prog->version[i];
if (!vers)
continue;
seq_printf(seq, "proc%u %u",
vers->number, vers->nrprocs);
for (j = 0; j < vers->nrprocs; j++)
seq_printf(seq, " %u", vers->counts[j]);
seq_putc(seq, '\n');
}
return 0;
}
static int rpc_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, rpc_proc_show, PDE_DATA(inode));
}
static const struct file_operations rpc_proc_fops = {
.owner = THIS_MODULE,
.open = rpc_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
/*
* Get RPC server stats
*/
void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp)
{
const struct svc_program *prog = statp->program;
const struct svc_version *vers;
unsigned int i, j;
seq_printf(seq,
"net %u %u %u %u\n",
statp->netcnt,
statp->netudpcnt,
statp->nettcpcnt,
statp->nettcpconn);
seq_printf(seq,
"rpc %u %u %u %u %u\n",
statp->rpccnt,
statp->rpcbadfmt+statp->rpcbadauth+statp->rpcbadclnt,
statp->rpcbadfmt,
statp->rpcbadauth,
statp->rpcbadclnt);
for (i = 0; i < prog->pg_nvers; i++) {
vers = prog->pg_vers[i];
if (!vers)
continue;
seq_printf(seq, "proc%d %u", i, vers->vs_nproc);
for (j = 0; j < vers->vs_nproc; j++)
seq_printf(seq, " %u", vers->vs_count[j]);
seq_putc(seq, '\n');
}
}
EXPORT_SYMBOL_GPL(svc_seq_show);
/**
* rpc_alloc_iostats - allocate an rpc_iostats structure
* @clnt: RPC program, version, and xprt
*
*/
struct rpc_iostats *rpc_alloc_iostats(struct rpc_clnt *clnt)
{
struct rpc_iostats *stats;
int i;
stats = kcalloc(clnt->cl_maxproc, sizeof(*stats), GFP_KERNEL);
if (stats) {
for (i = 0; i < clnt->cl_maxproc; i++)
spin_lock_init(&stats[i].om_lock);
}
return stats;
}
EXPORT_SYMBOL_GPL(rpc_alloc_iostats);
/**
* rpc_free_iostats - release an rpc_iostats structure
* @stats: doomed rpc_iostats structure
*
*/
void rpc_free_iostats(struct rpc_iostats *stats)
{
kfree(stats);
}
EXPORT_SYMBOL_GPL(rpc_free_iostats);
/**
* rpc_count_iostats_metrics - tally up per-task stats
* @task: completed rpc_task
* @op_metrics: stat structure for OP that will accumulate stats from @task
*/
void rpc_count_iostats_metrics(const struct rpc_task *task,
struct rpc_iostats *op_metrics)
{
struct rpc_rqst *req = task->tk_rqstp;
ktime_t backlog, execute, now;
if (!op_metrics || !req)
return;
nfs41: Add backchannel processing support to RPC state machine Adds rpc_run_bc_task() which is called by the NFS callback service to process backchannel requests. It performs similar work to rpc_run_task() though "schedules" the backchannel task to be executed starting at the call_trasmit state in the RPC state machine. It also introduces some miscellaneous updates to the argument validation, call_transmit, and transport cleanup functions to take into account that there are now forechannel and backchannel tasks. Backchannel requests do not carry an RPC message structure, since the payload has already been XDR encoded using the existing NFSv4 callback mechanism. Introduce a new transmit state for the client to reply on to backchannel requests. This new state simply reserves the transport and issues the reply. In case of a connection related error, disconnects the transport and drops the reply. It requires the forechannel to re-establish the connection and the server to retransmit the request, as stated in NFSv4.1 section 2.9.2 "Client and Server Transport Behavior". Note: There is no need to loop attempting to reserve the transport. If EAGAIN is returned by xprt_prepare_transmit(), return with tk_status == 0, setting tk_action to call_bc_transmit. rpc_execute() will invoke it again after the task is taken off the sleep queue. [nfs41: rpc_run_bc_task() need not be exported outside RPC module] [nfs41: New call_bc_transmit RPC state] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [nfs41: Backchannel: No need to loop in call_bc_transmit()] Signed-off-by: Andy Adamson <andros@netapp.com> Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [rpc_count_iostats incorrectly exits early] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com> [Convert rpc_reply_expected() to inline function] [Remove unnecessary BUG_ON()] [Rename variable] Signed-off-by: Ricardo Labiaga <Ricardo.Labiaga@netapp.com> Signed-off-by: Benny Halevy <bhalevy@panasas.com>
2009-04-01 20:23:03 +07:00
now = ktime_get();
spin_lock(&op_metrics->om_lock);
op_metrics->om_ops++;
2016-11-29 22:52:32 +07:00
/* kernel API: om_ops must never become larger than om_ntrans */
op_metrics->om_ntrans += max(req->rq_ntrans, 1);
op_metrics->om_timeouts += task->tk_timeouts;
op_metrics->om_bytes_sent += req->rq_xmit_bytes_sent;
op_metrics->om_bytes_recv += req->rq_reply_bytes_recvd;
backlog = 0;
2016-11-29 22:52:32 +07:00
if (ktime_to_ns(req->rq_xtime)) {
backlog = ktime_sub(req->rq_xtime, task->tk_start);
op_metrics->om_queue = ktime_add(op_metrics->om_queue, backlog);
2016-11-29 22:52:32 +07:00
}
op_metrics->om_rtt = ktime_add(op_metrics->om_rtt, req->rq_rtt);
execute = ktime_sub(now, task->tk_start);
op_metrics->om_execute = ktime_add(op_metrics->om_execute, execute);
spin_unlock(&op_metrics->om_lock);
trace_rpc_stats_latency(req->rq_task, backlog, req->rq_rtt, execute);
}
EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics);
/**
* rpc_count_iostats - tally up per-task stats
* @task: completed rpc_task
* @stats: array of stat structures
*
* Uses the statidx from @task
*/
void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
{
rpc_count_iostats_metrics(task,
&stats[task->tk_msg.rpc_proc->p_statidx]);
}
EXPORT_SYMBOL_GPL(rpc_count_iostats);
static void _print_name(struct seq_file *seq, unsigned int op,
const struct rpc_procinfo *procs)
{
if (procs[op].p_name)
seq_printf(seq, "\t%12s: ", procs[op].p_name);
else if (op == 0)
seq_printf(seq, "\t NULL: ");
else
seq_printf(seq, "\t%12u: ", op);
}
static void _add_rpc_iostats(struct rpc_iostats *a, struct rpc_iostats *b)
{
a->om_ops += b->om_ops;
a->om_ntrans += b->om_ntrans;
a->om_timeouts += b->om_timeouts;
a->om_bytes_sent += b->om_bytes_sent;
a->om_bytes_recv += b->om_bytes_recv;
a->om_queue = ktime_add(a->om_queue, b->om_queue);
a->om_rtt = ktime_add(a->om_rtt, b->om_rtt);
a->om_execute = ktime_add(a->om_execute, b->om_execute);
}
static void _print_rpc_iostats(struct seq_file *seq, struct rpc_iostats *stats,
int op, const struct rpc_procinfo *procs)
{
_print_name(seq, op, procs);
seq_printf(seq, "%lu %lu %lu %Lu %Lu %Lu %Lu %Lu\n",
stats->om_ops,
stats->om_ntrans,
stats->om_timeouts,
stats->om_bytes_sent,
stats->om_bytes_recv,
ktime_to_ms(stats->om_queue),
ktime_to_ms(stats->om_rtt),
ktime_to_ms(stats->om_execute));
}
sunrpc: Change rpc_print_iostats to rpc_clnt_show_stats and handle rpc_clnt clones The existing rpc_print_iostats has a few shortcomings. First, the naming is not consistent with other functions in the kernel that display stats. Second, it is really displaying stats for an rpc_clnt structure as it displays both xprt stats and per-op stats. Third, it does not handle rpc_clnt clones, which is important for the one in-kernel tree caller of this function, the NFS client's nfs_show_stats function. Fix all of the above by renaming the rpc_print_iostats to rpc_clnt_show_stats and looping through any rpc_clnt clones via cl_parent. Once this interface is fixed, this addresses a problem with NFSv4. Before this patch, the /proc/self/mountstats always showed incorrect counts for NFSv4 lease and session related opcodes such as SEQUENCE, RENEW, SETCLIENTID, CREATE_SESSION, etc. These counts were always 0 even though many ops would go over the wire. The reason for this is there are multiple rpc_clnt structures allocated for any given NFSv4 mount, and inside nfs_show_stats() we callled into rpc_print_iostats() which only handled one of them, nfs_server->client. Fix these counts by calling sunrpc's new rpc_clnt_show_stats() function, which handles cloned rpc_clnt structs and prints the stats together. Note that one side-effect of the above is that multiple mounts from the same NFS server will show identical counts in the above ops due to the fact the one rpc_clnt (representing the NFSv4 client state) is shared across mounts. Signed-off-by: Dave Wysochanski <dwysocha@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2018-07-31 21:10:51 +07:00
void rpc_clnt_show_stats(struct seq_file *seq, struct rpc_clnt *clnt)
{
struct rpc_xprt *xprt;
unsigned int op, maxproc = clnt->cl_maxproc;
sunrpc: Change rpc_print_iostats to rpc_clnt_show_stats and handle rpc_clnt clones The existing rpc_print_iostats has a few shortcomings. First, the naming is not consistent with other functions in the kernel that display stats. Second, it is really displaying stats for an rpc_clnt structure as it displays both xprt stats and per-op stats. Third, it does not handle rpc_clnt clones, which is important for the one in-kernel tree caller of this function, the NFS client's nfs_show_stats function. Fix all of the above by renaming the rpc_print_iostats to rpc_clnt_show_stats and looping through any rpc_clnt clones via cl_parent. Once this interface is fixed, this addresses a problem with NFSv4. Before this patch, the /proc/self/mountstats always showed incorrect counts for NFSv4 lease and session related opcodes such as SEQUENCE, RENEW, SETCLIENTID, CREATE_SESSION, etc. These counts were always 0 even though many ops would go over the wire. The reason for this is there are multiple rpc_clnt structures allocated for any given NFSv4 mount, and inside nfs_show_stats() we callled into rpc_print_iostats() which only handled one of them, nfs_server->client. Fix these counts by calling sunrpc's new rpc_clnt_show_stats() function, which handles cloned rpc_clnt structs and prints the stats together. Note that one side-effect of the above is that multiple mounts from the same NFS server will show identical counts in the above ops due to the fact the one rpc_clnt (representing the NFSv4 client state) is shared across mounts. Signed-off-by: Dave Wysochanski <dwysocha@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2018-07-31 21:10:51 +07:00
if (!clnt->cl_metrics)
return;
seq_printf(seq, "\tRPC iostats version: %s ", RPC_IOSTATS_VERS);
seq_printf(seq, "p/v: %u/%u (%s)\n",
clnt->cl_prog, clnt->cl_vers, clnt->cl_program->name);
rcu_read_lock();
xprt = rcu_dereference(clnt->cl_xprt);
if (xprt)
xprt->ops->print_stats(xprt, seq);
rcu_read_unlock();
seq_printf(seq, "\tper-op statistics\n");
for (op = 0; op < maxproc; op++) {
sunrpc: Change rpc_print_iostats to rpc_clnt_show_stats and handle rpc_clnt clones The existing rpc_print_iostats has a few shortcomings. First, the naming is not consistent with other functions in the kernel that display stats. Second, it is really displaying stats for an rpc_clnt structure as it displays both xprt stats and per-op stats. Third, it does not handle rpc_clnt clones, which is important for the one in-kernel tree caller of this function, the NFS client's nfs_show_stats function. Fix all of the above by renaming the rpc_print_iostats to rpc_clnt_show_stats and looping through any rpc_clnt clones via cl_parent. Once this interface is fixed, this addresses a problem with NFSv4. Before this patch, the /proc/self/mountstats always showed incorrect counts for NFSv4 lease and session related opcodes such as SEQUENCE, RENEW, SETCLIENTID, CREATE_SESSION, etc. These counts were always 0 even though many ops would go over the wire. The reason for this is there are multiple rpc_clnt structures allocated for any given NFSv4 mount, and inside nfs_show_stats() we callled into rpc_print_iostats() which only handled one of them, nfs_server->client. Fix these counts by calling sunrpc's new rpc_clnt_show_stats() function, which handles cloned rpc_clnt structs and prints the stats together. Note that one side-effect of the above is that multiple mounts from the same NFS server will show identical counts in the above ops due to the fact the one rpc_clnt (representing the NFSv4 client state) is shared across mounts. Signed-off-by: Dave Wysochanski <dwysocha@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2018-07-31 21:10:51 +07:00
struct rpc_iostats stats = {};
struct rpc_clnt *next = clnt;
do {
_add_rpc_iostats(&stats, &next->cl_metrics[op]);
if (next == next->cl_parent)
break;
next = next->cl_parent;
} while (next);
_print_rpc_iostats(seq, &stats, op, clnt->cl_procinfo);
}
}
sunrpc: Change rpc_print_iostats to rpc_clnt_show_stats and handle rpc_clnt clones The existing rpc_print_iostats has a few shortcomings. First, the naming is not consistent with other functions in the kernel that display stats. Second, it is really displaying stats for an rpc_clnt structure as it displays both xprt stats and per-op stats. Third, it does not handle rpc_clnt clones, which is important for the one in-kernel tree caller of this function, the NFS client's nfs_show_stats function. Fix all of the above by renaming the rpc_print_iostats to rpc_clnt_show_stats and looping through any rpc_clnt clones via cl_parent. Once this interface is fixed, this addresses a problem with NFSv4. Before this patch, the /proc/self/mountstats always showed incorrect counts for NFSv4 lease and session related opcodes such as SEQUENCE, RENEW, SETCLIENTID, CREATE_SESSION, etc. These counts were always 0 even though many ops would go over the wire. The reason for this is there are multiple rpc_clnt structures allocated for any given NFSv4 mount, and inside nfs_show_stats() we callled into rpc_print_iostats() which only handled one of them, nfs_server->client. Fix these counts by calling sunrpc's new rpc_clnt_show_stats() function, which handles cloned rpc_clnt structs and prints the stats together. Note that one side-effect of the above is that multiple mounts from the same NFS server will show identical counts in the above ops due to the fact the one rpc_clnt (representing the NFSv4 client state) is shared across mounts. Signed-off-by: Dave Wysochanski <dwysocha@redhat.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2018-07-31 21:10:51 +07:00
EXPORT_SYMBOL_GPL(rpc_clnt_show_stats);
/*
* Register/unregister RPC proc files
*/
static inline struct proc_dir_entry *
do_register(struct net *net, const char *name, void *data,
const struct file_operations *fops)
{
struct sunrpc_net *sn;
dprintk("RPC: registering /proc/net/rpc/%s\n", name);
sn = net_generic(net, sunrpc_net_id);
return proc_create_data(name, 0, sn->proc_net_rpc, fops, data);
}
struct proc_dir_entry *
rpc_proc_register(struct net *net, struct rpc_stat *statp)
{
return do_register(net, statp->program->name, statp, &rpc_proc_fops);
}
EXPORT_SYMBOL_GPL(rpc_proc_register);
void
rpc_proc_unregister(struct net *net, const char *name)
{
struct sunrpc_net *sn;
sn = net_generic(net, sunrpc_net_id);
remove_proc_entry(name, sn->proc_net_rpc);
}
EXPORT_SYMBOL_GPL(rpc_proc_unregister);
struct proc_dir_entry *
svc_proc_register(struct net *net, struct svc_stat *statp, const struct file_operations *fops)
{
return do_register(net, statp->program->pg_name, statp, fops);
}
EXPORT_SYMBOL_GPL(svc_proc_register);
void
svc_proc_unregister(struct net *net, const char *name)
{
struct sunrpc_net *sn;
sn = net_generic(net, sunrpc_net_id);
remove_proc_entry(name, sn->proc_net_rpc);
}
EXPORT_SYMBOL_GPL(svc_proc_unregister);
int rpc_proc_init(struct net *net)
{
struct sunrpc_net *sn;
dprintk("RPC: registering /proc/net/rpc\n");
sn = net_generic(net, sunrpc_net_id);
sn->proc_net_rpc = proc_mkdir("rpc", net->proc_net);
if (sn->proc_net_rpc == NULL)
return -ENOMEM;
return 0;
}
void rpc_proc_exit(struct net *net)
{
dprintk("RPC: unregistering /proc/net/rpc\n");
remove_proc_entry("rpc", net->proc_net);
}