LU-14139 statahead: add stats for batch RPC requests

This patch adds stats for batch PtlRPC request. It can show the
statistical information such as how many subreqs in a batch RPC.

Signed-off-by: Qian Yingjin <qian@ddn.com>
Change-Id: I2f71ff5d01ab1070bd8d771a72edd786ad27f03c
Reviewed-on: https://review.whamcloud.com/c/fs/lustre-release/+/40943
Tested-by: jenkins <devops@whamcloud.com>
Tested-by: Maloo <maloo@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Reviewed-by: Mikhail Pershin <mpershin@whamcloud.com>
Reviewed-by: Oleg Drokin <green@whamcloud.com>

diff --git a/lustre/include/obd.h b/lustre/include/obd.h
index e0fa3ce..1017c91 100644 (file)
--- a/lustre/include/obd.h
+++ b/lustre/include/obd.h
@@ -281,6 +281,8 @@ struct client_obd {
        struct obd_histogram    cl_write_page_hist;
        struct obd_histogram    cl_read_offset_hist;
        struct obd_histogram    cl_write_offset_hist;
+       ktime_t                 cl_batch_stats_init;
+       struct obd_histogram    cl_batch_rpc_hist;
 
        /** LRU for osc caching pages */
        struct cl_client_cache  *cl_cache;

diff --git a/lustre/ldlm/ldlm_lib.c b/lustre/ldlm/ldlm_lib.c
index 41b6b95..2ef3add 100644 (file)
--- a/lustre/ldlm/ldlm_lib.c
+++ b/lustre/ldlm/ldlm_lib.c
@@ -421,6 +421,7 @@ int client_obd_setup(struct obd_device *obd, struct lustre_cfg *lcfg)
        spin_lock_init(&cli->cl_write_page_hist.oh_lock);
        spin_lock_init(&cli->cl_read_offset_hist.oh_lock);
        spin_lock_init(&cli->cl_write_offset_hist.oh_lock);
+       spin_lock_init(&cli->cl_batch_rpc_hist.oh_lock);
 
        /* lru for osc. */
        INIT_LIST_HEAD(&cli->cl_lru_osc);

diff --git a/lustre/mdc/lproc_mdc.c b/lustre/mdc/lproc_mdc.c
index f932dfc..1dc5803 100644 (file)
--- a/lustre/mdc/lproc_mdc.c
+++ b/lustre/mdc/lproc_mdc.c
@@ -514,6 +514,48 @@ static int mdc_rpc_stats_seq_show(struct seq_file *seq, void *v)
 }
 LPROC_SEQ_FOPS(mdc_rpc_stats);
 
+static ssize_t mdc_batch_stats_seq_write(struct file *file,
+                                        const char __user *buf,
+                                        size_t len, loff_t *off)
+{
+       struct seq_file *seq = file->private_data;
+       struct obd_device *obd = seq->private;
+       struct client_obd *cli = &obd->u.cli;
+
+       lprocfs_oh_clear(&cli->cl_batch_rpc_hist);
+       cli->cl_batch_stats_init = ktime_get_real();
+
+       return len;
+}
+
+static int mdc_batch_stats_seq_show(struct seq_file *seq, void *v)
+{
+       struct obd_device *obd = seq->private;
+       struct client_obd *cli = &obd->u.cli;
+       unsigned long tot;
+       unsigned long cum;
+       int i;
+
+       lprocfs_stats_header(seq, ktime_get_real(), cli->cl_batch_stats_init,
+                            25, ":", true, "");
+       seq_printf(seq, "subreqs per batch   batches   %% cum %%\n");
+       tot = lprocfs_oh_sum(&cli->cl_batch_rpc_hist);
+       cum = 0;
+
+       for (i = 0; i < OBD_HIST_MAX; i++) {
+               unsigned long cnt = cli->cl_batch_rpc_hist.oh_buckets[i];
+
+               cum += cnt;
+               seq_printf(seq, "%d:\t\t%10lu %3u %3u\n",
+                          1 << i, cnt, pct(cnt, tot), pct(cum, tot));
+               if (cum == tot)
+                       break;
+       }
+
+       return 0;
+}
+LPROC_SEQ_FOPS(mdc_batch_stats);
+
 static int mdc_stats_seq_show(struct seq_file *seq, void *v)
 {
        struct obd_device *obd = seq->private;
@@ -632,6 +674,8 @@ struct lprocfs_vars lprocfs_mdc_obd_vars[] = {
          .fops =       &mdc_pinger_recov_fops          },
        { .name =       "rpc_stats",
          .fops =       &mdc_rpc_stats_fops             },
+       { .name =       "batch_stats",
+         .fops =       &mdc_batch_stats_fops           },
        { .name =       "unstable_stats",
          .fops =       &mdc_unstable_stats_fops        },
        { .name =       "mdc_stats",

diff --git a/lustre/ptlrpc/batch.c b/lustre/ptlrpc/batch.c
index 0cc8f88..d678211 100644 (file)
--- a/lustre/ptlrpc/batch.c
+++ b/lustre/ptlrpc/batch.c
@@ -36,6 +36,7 @@
 #define DEBUG_SUBSYSTEM S_MDC
 
 #include <linux/module.h>
+#include <obd_class.h>
 #include <obd.h>
 #ifdef HAVE_SERVER_SUPPORT
 #include <lustre_update.h>
@@ -410,9 +411,10 @@ static int batch_update_interpret(const struct lu_env *env,
 static int batch_send_update_req(const struct lu_env *env,
                                 struct batch_update_head *head)
 {
-       struct lu_batch *bh;
+       struct obd_device *obd;
        struct ptlrpc_request *req = NULL;
        struct batch_update_args *aa;
+       struct lu_batch *bh;
        int rc;
 
        ENTRY;
@@ -420,6 +422,7 @@ static int batch_send_update_req(const struct lu_env *env,
        if (head == NULL)
                RETURN(0);
 
+       obd = class_exp2obd(head->buh_exp);
        bh = head->buh_batch;
        rc = batch_prep_update_req(head, &req);
        if (rc) {
@@ -456,6 +459,8 @@ static int batch_send_update_req(const struct lu_env *env,
        if (req != NULL)
                ptlrpc_req_finished(req);
 
+       lprocfs_oh_tally_log2(&obd->u.cli.cl_batch_rpc_hist,
+                             head->buh_update_count);
        RETURN(rc);
 }
 

diff --git a/lustre/tests/sanity.sh b/lustre/tests/sanity.sh
index 77b706a..0d23256 100755 (executable)
--- a/lustre/tests/sanity.sh
+++ b/lustre/tests/sanity.sh
@@ -13575,6 +13575,8 @@ test_123a_base() { # was test 123, statahead(bug 11401)
        fi
        running_in_vm && SLOWOK=1
 
+       $LCTL set_param mdc.*.batch_stats=0
+
        rm -rf $DIR/$tdir
        test_mkdir $DIR/$tdir
        NUMFREE=$(df -i -P $DIR | tail -n 1 | awk '{ print $4 }')
@@ -13650,6 +13652,7 @@ test_123a_base() { # was test 123, statahead(bug 11401)
        log "rm -r $DIR/$tdir/: $delta seconds"
        log "rm done"
        lctl get_param -n llite.*.statahead_stats
+       $LCTL get_param mdc.*.batch_stats
 }
 
 test_123aa() {