From: Zhi Zhang <zhang.david2011@gmail.com>
To: ceph-devel <ceph-devel@vger.kernel.org>, Zheng Yan <zyan@redhat.com>
Subject: [PATCH] ceph: try to allocate enough memory for reserved caps
Date: Wed, 24 Jan 2018 10:58:32 +0800 [thread overview]
Message-ID: <CAGkCoNKp=0TqoxL9u3pFehuS2MkpSK0NDmNPrncYULKRMxxmMw@mail.gmail.com> (raw)
ceph_reserve_caps may not reserve enough caps under high memory
pressure, but it saved the needed caps number that expected to
be reserved. When getting caps, crash would happen due to number
mismatch.
Now we will try to trim more caps when failing to allocate memory
for caps need to be reserved, then try again. If still failing to
allocate memory, return ENOMEM.
Signed-off-by: Zhi Zhang <zhang.david2011@gmail.com>
---
fs/ceph/caps.c | 62
++++++++++++++++++++++++++++++++++++++++++++++++++++++--------
fs/ceph/mds_client.c | 24 +++++++++++++++++-------
fs/ceph/mds_client.h | 3 +++
fs/ceph/super.h | 2 +-
4 files changed, 75 insertions(+), 16 deletions(-)
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index a14b2c9..6784f59 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -154,13 +154,19 @@ void ceph_adjust_min_caps(struct ceph_mds_client
*mdsc, int delta)
spin_unlock(&mdsc->caps_list_lock);
}
-void ceph_reserve_caps(struct ceph_mds_client *mdsc,
+/*
+ * Called under mdsc->mutex.
+ */
+int ceph_reserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx, int need)
{
- int i;
+ int i, j;
struct ceph_cap *cap;
int have;
int alloc = 0;
+ int max_caps;
+ bool trimmed = false;
+ struct ceph_mds_session *s;
LIST_HEAD(newcaps);
dout("reserve caps ctx=%p need=%d\n", ctx, need);
@@ -179,16 +185,38 @@ void ceph_reserve_caps(struct ceph_mds_client *mdsc,
spin_unlock(&mdsc->caps_list_lock);
for (i = have; i < need; i++) {
+retry:
cap = kmem_cache_alloc(ceph_cap_cachep, GFP_NOFS);
- if (!cap)
- break;
+ if (!cap) {
+ if (!trimmed) {
+ for (j = 0; j < mdsc->max_sessions; j++) {
+ s = __ceph_lookup_mds_session(mdsc, j);
+ if (!s)
+ continue;
+ mutex_unlock(&mdsc->mutex);
+
+ // trim needed caps to free memory
+ mutex_lock(&s->s_mutex);
+ max_caps = s->s_nr_caps - (need - i);
+ ceph_trim_caps(mdsc, s, max_caps);
+ mutex_unlock(&s->s_mutex);
+
+ ceph_put_mds_session(s);
+ mutex_lock(&mdsc->mutex);
+ }
+ trimmed = true;
+ goto retry;
+ } else {
+ pr_warn("reserve caps ctx=%p ENOMEM "
+ "need=%d got=%d\n",
+ ctx, need, have + alloc);
+ goto out_nomem;
+ }
+ }
list_add(&cap->caps_item, &newcaps);
alloc++;
}
- /* we didn't manage to reserve as much as we needed */
- if (have + alloc != need)
- pr_warn("reserve caps ctx=%p ENOMEM need=%d got=%d\n",
- ctx, need, have + alloc);
+ BUG_ON(have + alloc != need);
spin_lock(&mdsc->caps_list_lock);
mdsc->caps_total_count += alloc;
@@ -204,6 +232,24 @@ void ceph_reserve_caps(struct ceph_mds_client *mdsc,
dout("reserve caps ctx=%p %d = %d used + %d resv + %d avail\n",
ctx, mdsc->caps_total_count, mdsc->caps_use_count,
mdsc->caps_reserve_count, mdsc->caps_avail_count);
+ return 0;
+
+out_nomem:
+ while (!list_empty(&newcaps)) {
+ cap = list_first_entry(&newcaps,
+ struct ceph_cap, caps_item);
+ list_del(&cap->caps_item);
+ kmem_cache_free(ceph_cap_cachep, cap);
+ }
+
+ spin_lock(&mdsc->caps_list_lock);
+ mdsc->caps_avail_count += have;
+ mdsc->caps_reserve_count -= have;
+ BUG_ON(mdsc->caps_total_count != mdsc->caps_use_count +
+ mdsc->caps_reserve_count +
+ mdsc->caps_avail_count);
+ spin_unlock(&mdsc->caps_list_lock);
+ return -ENOMEM;
}
int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 1b46825..abc0375 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -604,10 +604,20 @@ static void __register_request(struct
ceph_mds_client *mdsc,
struct ceph_mds_request *req,
struct inode *dir)
{
+ int ret = 0;
+
req->r_tid = ++mdsc->last_tid;
- if (req->r_num_caps)
- ceph_reserve_caps(mdsc, &req->r_caps_reservation,
- req->r_num_caps);
+ if (req->r_num_caps) {
+ ret = ceph_reserve_caps(mdsc, &req->r_caps_reservation,
+ req->r_num_caps);
+ if (ret) {
+ pr_err("__register_request %p "
+ "failed to reserve caps: %d\n", req, ret);
+ // set req->r_err to fail early from __do_request
+ req->r_err = ret;
+ return;
+ }
+ }
dout("__register_request %p tid %lld\n", req, req->r_tid);
ceph_mdsc_get_request(req);
insert_request(&mdsc->request_tree, req);
@@ -1545,9 +1555,9 @@ static int trim_caps_cb(struct inode *inode,
struct ceph_cap *cap, void *arg)
/*
* Trim session cap count down to some max number.
*/
-static int trim_caps(struct ceph_mds_client *mdsc,
- struct ceph_mds_session *session,
- int max_caps)
+int ceph_trim_caps(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session,
+ int max_caps)
{
int trim_caps = session->s_nr_caps - max_caps;
@@ -2773,7 +2783,7 @@ static void handle_session(struct
ceph_mds_session *session,
break;
case CEPH_SESSION_RECALL_STATE:
- trim_caps(mdsc, session, le32_to_cpu(h->max_caps));
+ ceph_trim_caps(mdsc, session, le32_to_cpu(h->max_caps));
break;
case CEPH_SESSION_FLUSHMSG:
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 837ac4b..f9160f4 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -444,4 +444,7 @@ extern void ceph_mdsc_handle_fsmap(struct
ceph_mds_client *mdsc,
extern void ceph_mdsc_open_export_target_sessions(struct ceph_mds_client *mdsc,
struct ceph_mds_session *session);
+extern int ceph_trim_caps(struct ceph_mds_client *mdsc,
+ struct ceph_mds_session *session,
+ int max_caps);
#endif
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 2beeec0..e5fee4f 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -648,7 +648,7 @@ static inline int __ceph_caps_wanted(struct
ceph_inode_info *ci)
extern void ceph_caps_init(struct ceph_mds_client *mdsc);
extern void ceph_caps_finalize(struct ceph_mds_client *mdsc);
extern void ceph_adjust_min_caps(struct ceph_mds_client *mdsc, int delta);
-extern void ceph_reserve_caps(struct ceph_mds_client *mdsc,
+extern int ceph_reserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx, int need);
extern int ceph_unreserve_caps(struct ceph_mds_client *mdsc,
struct ceph_cap_reservation *ctx);
Regards,
Zhi Zhang (David)
Contact: zhang.david2011@gmail.com
zhangz.david@outlook.com
next reply other threads:[~2018-01-24 2:59 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-24 2:58 Zhi Zhang [this message]
2018-01-24 10:53 [PATCH] ceph: try to allocate enough memory for reserved caps Zhi Zhang
2018-01-24 13:24 Zhi Zhang
2018-01-24 14:08 ` Yan, Zheng
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='CAGkCoNKp=0TqoxL9u3pFehuS2MkpSK0NDmNPrncYULKRMxxmMw@mail.gmail.com' \
--to=zhang.david2011@gmail.com \
--cc=ceph-devel@vger.kernel.org \
--cc=zyan@redhat.com \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.