…t_max

Backport: firefly

Signed-off-by: David Zafman <david.zafman@inktank.com>
(cherry picked from commit 9cf470c)

…t) secs

Add config osd_agent_delay_time of 5 seconds
Honor delay by ignoring agent_choose_mode() calls
Add tier_delay to logger
Treat restart after delay like we were previously idle

Fixes: ceph#8113
Backport: firefly

Signed-off-by: David Zafman <david.zafman@inktank.com>
(cherry picked from commit b7d31e5)

Fixes: ceph#8175
Backport: firefly

Signed-off-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit f47f867)

We were special casing WRITEBACK mode for handling whiteouts; this needs to
also include the FORWARD and READONLY modes.  To avoid having to list
specific cache modes, though, just check != NONE.

Fixes: ceph#8296
Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3e387d6)

We normally need to stat the hit_set to know how many bytes to adjust the
stats by.  If the hit_set was just written, we will get ENOENT.

Get the obc instead, which will either get the in-memory copy (because the
repop is still in flight) or load it off of disk.

Fixes: ceph#8283
Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 72fdd55)

Callig _finish_hunting() clears out the bool hunting flag, which means we
don't retry by connection to another mon periodically.  Instead, we send
keepalives every 10s.  But, since we aren't yet in state HAVE_SESSION, we
don't check that the keepalives are getting responses.  This means that an
ill-timed connection reset (say, after we get a MonMap, but before we
finish authenticating) can drop the monc into a black hole that does not
retry.

Instead, we should *only* call _finish_hunting() when we complete the
authentication handshake.

Fixes: ceph#8278
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 77a6f0a)

This is not particularly smart, but it is *a* knob that lets you make
the snap trimmer slow down.  It's a flow and a simple delay, so it is
adjustable at runtime.  Default is 0 (no change in behavior).

Partial solution for ceph#6278.

Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 4413670)

Fixes: ceph#8021
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
(cherry picked from commit 09a1bc5)

Fixes: ceph#8170
Backport: firefly
If user manifest header exists (swift) send it as part of the object
header data.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 5cc5686)

Fixes: ceph#8289
Backport: firefly, dumpling
When reading an object, if we hit an error when trying to read one of
the rados objects then we should just stop. Otherwise we're just going
to continue reading the rest of the object, and since it can't be sent
back to the client (as we have a hole in the middle), we end up
accumulating everything in memory.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 03b0d1c)

Fixes: ceph#8299
Backport: firefly
The stripe size calculation was broken, specifically affected cases
where we had manifest that described multiple parts.

Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 9968b93)

This reverts commit e66f2e3.
Reviewed-by: Sage Weil <sage@inktank.com>

0f3235d is the firefly commit
corresponding to e66f2e3.

(cherry picked from commit 8472805)

We call start_flush() with a NULL op in a couple different places.  Do not
put a NULL pointer on the dup_ops list or we will crash later.

Fixes: ceph#8328
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 0d67f9b)

If we get a MOSDMarkMeDown message and set service.state == STOPPING, we
kick the prepare_to_stop() thread.  Normally, it will wake up and then
set osd.state == STOPPING, and when we process the map message next we
will not warn.  However, if dispatch() takes the lock instead and processes
the map, it will fail the preparing_to_stop check and issue a spurious
warning.

Fix by checking for either preparing_to_stop or stopping.

Fixes: ceph#8319
Backport: firefly, emperor, dumpling
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 6b858be)

Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3152faf)

If we are a client, and process a map that sets last_force_op_resend to
the current epoch, force a resend of this op.

If the OSD expects us to do this, it will discard our previous op.  If the
OSD is old, it will process the old one, this will appear as a dup, and we
are no worse off than before.

Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit dd700bd)

If an op is sent before last_force_op_resend, and the client's feature is
present, drop the op because we know they will resend.

Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 45e79a1)

If a client is sending a sequence of ops (say, a, b, c, d) and partway
through that sequence it receives an OSDMap update that changes the
overlay, the ops will get send to different pools, and the replies will
come back completely out of order.

To fix this, force a resend of all outstanding ops any time the overlay
changes.

Fixes: ceph#8305
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 63d92ab)

Otherwise, redirected ops will suddenly have a different tid
and will become uncancelable.

Fixes: ceph#7588
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 76568aa)

…reset

Backport: firefly, emperor, dumpling

Signed-off-by: Guang Yang (yguang@yahoo-inc.com)
Reviewed-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit bdee119)

Fixes: ceph#8011
Backport: firefly
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 7411477)

When we send redirected ops, we do not assign a new tid, which means that
a given client's ops for a pool may not have strictly ordered tids.  Skip
this check if the pool is tiered to avoid false positives.

Fixes: ceph#8380
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit cf2b172)

When calling osdmap_subscribe, you have to pass an epoch newer than the
current map's. _maybe_boot() was not doing this correctly -- we would
fail a check for being *in* the monitor's existing map range, and then
pass along the map prior to the monitor's range. But if we were exactly
one behind, that value would be our current epoch, and the request would
get dropped. So instead, make sure we are not *in contact* with the monitor's
existing map range.

Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 290ac81)

Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 00225d7)

Two users have reported this fixes a problem with using --dmcrypt.

Fixes: ceph#6966
Tested-by: Eric Eastman <eric0e@aol.com>
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 0f19626)

…iable).

 This should not affect OpenJDK which understands '-classpath' as well.

 With gcj-jdk we still get FTBFS later:

 ~~~~
    java/native/libcephfs_jni.cc:2878:55: error: invalid conversion from 'const jbyte* {aka const signed char*}' to 'jbyte* {aka signed char*}' [-fpermissive]
                 reinterpret_cast<const jbyte*>(rawAddress));
                                                           ^
    In file included from java/native/libcephfs_jni.cc:27:0:
    /usr/lib/gcc/x86_64-linux-gnu/4.8/include/jni.h:1471:8: error:   initializing argument 4 of 'void _Jv_JNIEnv::SetByteArrayRegion(jbyteArray, jsize, jsize, jbyte*)' [-fpermissive]
       void SetByteArrayRegion (jbyteArray val0, jsize val1, jsize val2, jbyte * val3)
            ^
    make[5] *** [java/native/libcephfs_jni_la-libcephfs_jni.lo] Error 1
 ~~~~

Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
(cherry picked from commit 89fe035)

…tives).

 On Debian this fixes FTBFS when gcj-jdk and openjdk-7-jdk are installed at
 the same time because build system will use default `javac` executable
 provided by current JDK through `update-alternatives` instead of blindly
 calling GCJ when it is present.

Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
(cherry picked from commit 8b682d1)

Commit 8c5c55c ("mon: set next commit in mon command replies")
fixed MMonCommand replies to include the right version, but the
primary-affinity handler was authored before that.  Fix it.

Backport: firefly
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
(cherry picked from commit a78b14e)

Older versions of the JNI interface expected non-const parameters
to their memory move functions. It's unpleasant, but won't actually
change the memory in question, to do a cast_const in order to satisfy
those older headers. (And even if it *did* modify the memory, that
would be okay given our single user.)

Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit 4d4b77e)