This is a note to let you know that I've just added the patch titled
crush: ensuring at most num-rep osds are selected
to the 4.0-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
crush-ensuring-at-most-num-rep-osds-are-selected.patch
and it can be found in the queue-4.0 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <[email protected]> know about it.
>From 45002267e8d2699bf9b022315bee3dd13b044843 Mon Sep 17 00:00:00 2001
From: Ilya Dryomov <[email protected]>
Date: Tue, 14 Apr 2015 16:04:23 +0300
Subject: crush: ensuring at most num-rep osds are selected
From: Ilya Dryomov <[email protected]>
commit 45002267e8d2699bf9b022315bee3dd13b044843 upstream.
Crush temporary buffers are allocated as per replica size configured
by the user. When there are more final osds (to be selected as per
rule) than the replicas, buffer overlaps and it causes crash. Now, it
ensures that at most num-rep osds are selected even if more number of
osds are allowed by the rule.
Reflects ceph.git commits 6b4d1aa99718e3b367496326c1e64551330fabc0,
234b066ba04976783d15ff2abc3e81b6cc06fb10.
Signed-off-by: Ilya Dryomov <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
---
net/ceph/crush/mapper.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
--- a/net/ceph/crush/mapper.c
+++ b/net/ceph/crush/mapper.c
@@ -290,6 +290,7 @@ static int is_out(const struct crush_map
* @type: the type of item to choose
* @out: pointer to output vector
* @outpos: our position in that vector
+ * @out_size: size of the out vector
* @tries: number of attempts to make
* @recurse_tries: number of attempts to have recursive chooseleaf make
* @local_retries: localized retries
@@ -304,6 +305,7 @@ static int crush_choose_firstn(const str
const __u32 *weight, int weight_max,
int x, int numrep, int type,
int *out, int outpos,
+ int out_size,
unsigned int tries,
unsigned int recurse_tries,
unsigned int local_retries,
@@ -322,6 +324,7 @@ static int crush_choose_firstn(const str
int item = 0;
int itemtype;
int collide, reject;
+ int count = out_size;
dprintk("CHOOSE%s bucket %d x %d outpos %d numrep %d tries %d
recurse_tries %d local_retries %d local_fallback_retries %d parent_r %d\n",
recurse_to_leaf ? "_LEAF" : "",
@@ -329,7 +332,7 @@ static int crush_choose_firstn(const str
tries, recurse_tries, local_retries, local_fallback_retries,
parent_r);
- for (rep = outpos; rep < numrep; rep++) {
+ for (rep = outpos; rep < numrep && count > 0 ; rep++) {
/* keep trying until we get a non-out, non-colliding item */
ftotal = 0;
skip_rep = 0;
@@ -403,7 +406,7 @@ static int crush_choose_firstn(const str
map->buckets[-1-item],
weight, weight_max,
x, outpos+1, 0,
- out2, outpos,
+ out2, outpos, count,
recurse_tries, 0,
local_retries,
local_fallback_retries,
@@ -463,6 +466,7 @@ reject:
dprintk("CHOOSE got %d\n", item);
out[outpos] = item;
outpos++;
+ count--;
}
dprintk("CHOOSE returns %d\n", outpos);
@@ -654,6 +658,7 @@ int crush_do_rule(const struct crush_map
__u32 step;
int i, j;
int numrep;
+ int out_size;
/*
* the original choose_total_tries value was off by one (it
* counted "retries" and not "tries"). add one.
@@ -761,6 +766,7 @@ int crush_do_rule(const struct crush_map
x, numrep,
curstep->arg2,
o+osize, j,
+ result_max-osize,
choose_tries,
recurse_tries,
choose_local_retries,
@@ -770,11 +776,13 @@ int crush_do_rule(const struct crush_map
c+osize,
0);
} else {
+ out_size = ((numrep <
(result_max-osize)) ?
+ numrep :
(result_max-osize));
crush_choose_indep(
map,
map->buckets[-1-w[i]],
weight, weight_max,
- x, numrep, numrep,
+ x, out_size, numrep,
curstep->arg2,
o+osize, j,
choose_tries,
@@ -783,7 +791,7 @@ int crush_do_rule(const struct crush_map
recurse_to_leaf,
c+osize,
0);
- osize += numrep;
+ osize += out_size;
}
}
Patches currently in stable-queue which might be from [email protected] are
queue-4.0/crush-ensuring-at-most-num-rep-osds-are-selected.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
