Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1157639

[PATCH 3.14 12/64] libceph: request a new osdmap if lingering request maps to no osd

From Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Newsgroups linux.kernel
Subject [PATCH 3.14 12/64] libceph: request a new osdmap if lingering request maps to no osd
Date 2015-06-03 15:10 +0200
Message-ID <pxgAI-1Uo-59@gated-at.bofh.it> (permalink)
References <pxfOh-E4-7@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

3.14-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ilya Dryomov <idryomov@gmail.com>

commit b0494532214bdfbf241e94fabab5dd46f7b82631 upstream.

This commit does two things.  First, if there are any homeless
lingering requests, we now request a new osdmap even if the osdmap that
is being processed brought no changes, i.e. if a given lingering
request turned homeless in one of the previous epochs and remained
homeless in the current epoch.  Not doing so leaves us with a stale
osdmap and as a result we may miss our window for reestablishing the
watch and lose notifies.

MON=1 OSD=1:

    # cat linger-needmap.sh
    #!/bin/bash
    rbd create --size 1 test
    DEV=$(rbd map test)
    ceph osd out 0
    rbd map dne/dne # obtain a new osdmap as a side effect (!)
    sleep 1
    ceph osd in 0
    rbd resize --size 2 test
    # rbd info test | grep size -> 2M
    # blockdev --getsize $DEV -> 1M

N.B.: Not obtaining a new osdmap in between "osd out" and "osd in"
above is enough to make it miss that resize notify, but that is a
bug^Wlimitation of ceph watch/notify v1.

Second, homeless lingering requests are now kicked just like those
lingering requests whose mapping has changed.  This is mainly to
recognize that a homeless lingering request makes no sense and to
preserve the invariant that a registered lingering request is not
sitting on any of r_req_lru_item lists.  This spares us a WARN_ON,
which commit ba9d114ec557 ("libceph: clear r_req_lru_item in
__unregister_linger_request()") tried to fix the _wrong_ way.

Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Reviewed-by: Sage Weil <sage@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 net/ceph/osd_client.c |   31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -1932,20 +1932,29 @@ static void kick_requests(struct ceph_os
 		err = __map_request(osdc, req,
 				    force_resend || force_resend_writes);
 		dout("__map_request returned %d\n", err);
-		if (err == 0)
-			continue;  /* no change and no osd was specified */
 		if (err < 0)
 			continue;  /* hrm! */
-		if (req->r_osd == NULL) {
-			dout("tid %llu maps to no valid osd\n", req->r_tid);
-			needmap++;  /* request a newer map */
-			continue;
-		}
+		if (req->r_osd == NULL || err > 0) {
+			if (req->r_osd == NULL) {
+				dout("lingering %p tid %llu maps to no osd\n",
+				     req, req->r_tid);
+				/*
+				 * A homeless lingering request makes
+				 * no sense, as it's job is to keep
+				 * a particular OSD connection open.
+				 * Request a newer map and kick the
+				 * request, knowing that it won't be
+				 * resent until we actually get a map
+				 * that can tell us where to send it.
+				 */
+				needmap++;
+			}
 
-		dout("kicking lingering %p tid %llu osd%d\n", req, req->r_tid,
-		     req->r_osd ? req->r_osd->o_osd : -1);
-		__register_request(osdc, req);
-		__unregister_linger_request(osdc, req);
+			dout("kicking lingering %p tid %llu osd%d\n", req,
+			     req->r_tid, req->r_osd ? req->r_osd->o_osd : -1);
+			__register_request(osdc, req);
+			__unregister_linger_request(osdc, req);
+		}
 	}
 	reset_changed_osds(osdc);
 	mutex_unlock(&osdc->request_mutex);


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 3.14 00/64] 3.14.44-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 31/64] USB: pl2303: Remove support for Samsung I330 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 03/64] staging: rtl8712, rtl8712: avoid lots of build warnings Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 19/64] ALSA: hda - Add headphone quirk for Lifebook E752 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 58/64] sd: Disable support for 256 byte/sector disks Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 29/64] xhci: gracefully handle xhci_irq dead device Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 44/64] gpio: gpio-kempld: Fix get_direction return value Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 52/64] thermal: step_wise: Revert optimization Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 08/64] net: socket: Fix the wrong returns for recvmsg and sendmsg Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 56/64] Input: elantech - fix semi-mt protocol for v3 HW Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 04/64] staging, rtl8192e, LLVMLinux: Remove unused inline prototype Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 40/64] jbd2: fix r_count overflows leading to buffer overflow in journal recovery Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 14/64] hwmon: (ntc_thermistor) Ensure iio channel is of type IIO_VOLTAGE Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 45/64] crypto: s390/ghash - Fix incorrect ghash icv buffer handling. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 64/64] fs/binfmt_elf.c:load_elf_binary(): return -EINVAL on zero-length mappings Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 41/64] libata: Add helper to determine when PHY events should be ignored Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 18/64] ALSA: hda - Add Conexant codecs CX20721, CX20722, CX20723 and CX20724 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:20 +0200
  [PATCH 3.14 32/64] USB: cp210x: add ID for KCF Technologies PRN device Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 49/64] tools/vm: fix page-flags build Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 53/64] md/raid5: dont record new size if resize_stripes fails. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 09/64] fs, omfs: add NULL terminator in the end up the token list Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 23/64] ASoC: wm8960: fix "RINPUT3" audio route error Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 50/64] mm, numa: really disable NUMA balancing by default on single node machines Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 37/64] tty/n_gsm.c: fix a memory leak when gsmtty is removed Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 35/64] powerpc: Align TOC to 256 bytes Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 11/64] lguest: fix out-by-one error in address checking. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 51/64] svcrpc: fix potential GSSX_ACCEPT_SEC_CONTEXT decoding failures Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 12/64] libceph: request a new osdmap if lingering request maps to no osd Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 07/64] KVM: MMU: fix CR4.SMEP=1, CR0.WP=0 with shadow pages Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 10/64] xfs: xfs_iozero can return positive errno Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 54/64] md/raid0: fix restore to sector variable in raid0_make_request Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  [PATCH 3.14 55/64] rtlwifi: rtl8192cu: Fix kernel deadlock Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 15:10 +0200
  Re: [PATCH 3.14 00/64] 3.14.44-stable review Shuah Khan <shuahkh@osg.samsung.com> - 2015-06-03 19:00 +0200

csiph-web