CEPH filesystem development
 help / color / mirror / Atom feed
From: "Yan, Zheng" <zyan@redhat.com>
To: ceph-devel@vger.kernel.org
Cc: idryomov@gmail.com, "Yan, Zheng" <zyan@redhat.com>
Subject: [PATCH V2 3/6] libceph: allow reserving operations in OSD request
Date: Tue, 19 Jan 2016 16:08:08 +0800	[thread overview]
Message-ID: <1453190891-40937-4-git-send-email-zyan@redhat.com> (raw)
In-Reply-To: <1453190891-40937-1-git-send-email-zyan@redhat.com>

This allows us to reserve some operations for furture use. we do
not need to use all reserved operations.

Signed-off-by: Yan, Zheng <zyan@redhat.com>
---
 include/linux/ceph/osd_client.h | 1 +
 net/ceph/osd_client.c           | 7 +++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fda3a05..9802df1 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -139,6 +139,7 @@ struct ceph_osd_request {
 	u32               r_sent;      /* >0 if r_request is sending/sent */
 
 	/* request osd ops array  */
+	unsigned int		r_max_ops;
 	unsigned int		r_num_ops;
 	struct ceph_osd_req_op	*r_ops;
 	struct ceph_osd_req_op	r_inline_ops[CEPH_OSD_INITIAL_OP];
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 3852006..9c0cf2e 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -385,7 +385,8 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 
 	req->r_osdc = osdc;
 	req->r_mempool = use_mempool;
-	req->r_num_ops = num_ops;
+	req->r_num_ops = 0;
+	req->r_max_ops = num_ops;
 
 	if (num_ops <= CEPH_OSD_INITIAL_OP) {
 		req->r_ops = req->r_inline_ops;
@@ -480,8 +481,10 @@ _osd_req_op_init(struct ceph_osd_request *osd_req, unsigned int which,
 {
 	struct ceph_osd_req_op *op;
 
-	BUG_ON(which >= osd_req->r_num_ops);
+	BUG_ON(which >= osd_req->r_max_ops);
 	BUG_ON(!osd_req_opcode_valid(opcode));
+	if (which >= osd_req->r_num_ops)
+		osd_req->r_num_ops = which + 1;
 
 	op = &osd_req->r_ops[which];
 	memset(op, 0, sizeof (*op));
-- 
2.5.0


  parent reply	other threads:[~2016-01-19  8:08 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-01-19  8:08 [PATCH V2 0/6] scattered page writeback Yan, Zheng
2016-01-19  8:08 ` [PATCH V2 1/6] libceph: enlarge max number of operations in OSD request Yan, Zheng
2016-01-19  8:08 ` [PATCH V2 2/6] libceph: move r_reply_op_{len,result} into struct ceph_osd_req_op Yan, Zheng
2016-01-19  8:08 ` Yan, Zheng [this message]
2016-01-19  8:08 ` [PATCH V2 4/6] libceph: add helper that extends numner of operations in OSD request Yan, Zheng
2016-01-19  8:08 ` [PATCH V2 5/6] libceph: add helper that duplicates last extent operation Yan, Zheng
2016-01-19  8:08 ` [PATCH V2 6/6] ceph: scattered page writeback 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=1453190891-40937-4-git-send-email-zyan@redhat.com \
    --to=zyan@redhat.com \
    --cc=ceph-devel@vger.kernel.org \
    --cc=idryomov@gmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox