From: Jeff Layton <jlayton@redhat.com>
To: bfields@fieldses.org
Cc: linux-nfs@vger.kernel.org
Subject: [PATCH v2 5/5] nfsd: keep track of the max and average time to search the cache
Date: Thu, 21 Feb 2013 13:28:38 -0500 [thread overview]
Message-ID: <1361471318-17971-6-git-send-email-jlayton@redhat.com> (raw)
In-Reply-To: <1361471318-17971-1-git-send-email-jlayton@redhat.com>
Since we're moderately concerned about the potential increase in hash
chain lengths, keep a running average of the time and the max time to
search.
Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
fs/nfsd/nfscache.c | 25 +++++++++++++++++++++----
1 file changed, 21 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index 52493cb..ae6575d 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -33,6 +33,9 @@ static unsigned int max_drc_entries; /* max number of entries */
static unsigned int drc_mem_usage; /* memory used by cache */
static unsigned int csum_misses; /* cache misses due only to
csum comparison failures */
+static unsigned int max_search_time; /* max time to search */
+static unsigned int avg_search_time; /* avg time to search */
+
/*
* Calculate the hash index from an XID.
*/
@@ -310,16 +313,28 @@ nfsd_cache_match(struct svc_rqst *rqstp, __wsum csum, struct svc_cacherep *rp)
static struct svc_cacherep *
nfsd_cache_search(struct svc_rqst *rqstp, __wsum csum)
{
- struct svc_cacherep *rp;
+ struct svc_cacherep *rp, *ret = NULL;
struct hlist_node *hn;
struct hlist_head *rh;
+ ktime_t start;
+ unsigned int delta;
+ static unsigned int nsearches = 0;
+ unsigned int osearches;
+ start = ktime_get();
rh = &cache_hash[request_hash(rqstp->rq_xid)];
hlist_for_each_entry(rp, hn, rh, c_hash) {
- if (nfsd_cache_match(rqstp, csum, rp))
- return rp;
+ if (nfsd_cache_match(rqstp, csum, rp)) {
+ ret = rp;
+ break;
+ }
}
- return NULL;
+ delta = (unsigned int)ktime_to_ns(ktime_sub(ktime_get(), start));
+ osearches = nsearches++;
+ avg_search_time = (avg_search_time * osearches + delta) / nsearches;
+ max_search_time = max(max_search_time, delta);
+
+ return ret;
}
/*
@@ -589,6 +604,8 @@ static int nfsd_reply_cache_stats_show(struct seq_file *m, void *v)
seq_printf(m, "not cached: %u\n", nfsdstats.rcnocache);
seq_printf(m, "checksum misses: %u\n", csum_misses);
seq_printf(m, "max chain len: %u\n", nfsd_repcache_max_chain_len());
+ seq_printf(m, "avg search time: %uns\n", avg_search_time);
+ seq_printf(m, "max search time: %uns\n", max_search_time);
spin_unlock(&cache_lock);
return 0;
}
--
1.7.11.7
prev parent reply other threads:[~2013-02-21 18:28 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-21 18:28 [PATCH v2 0/5] nfsd: add a reply_cache_stats file to nfsd for tracking DRC performance Jeff Layton
2013-02-21 18:28 ` [PATCH v2 1/5] nfsd: break out comparator into separate function Jeff Layton
2013-02-21 18:28 ` [PATCH v2 2/5] nfsd: track memory utilization in the DRC Jeff Layton
2013-02-21 18:28 ` [PATCH v2 3/5] nfsd: add new reply_cache_stats file in nfsdfs Jeff Layton
2013-02-21 18:28 ` [PATCH v2 4/5] nfsd: report length of the longest hash chain in reply cache stats Jeff Layton
2013-02-21 18:28 ` Jeff Layton [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1361471318-17971-6-git-send-email-jlayton@redhat.com \
--to=jlayton@redhat.com \
--cc=bfields@fieldses.org \
--cc=linux-nfs@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).