Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1157364
| From | Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH 3.10 11/46] libceph: request a new osdmap if lingering request maps to no osd |
| Date | 2015-06-03 13:50 +0200 |
| Message-ID | <pxflg-8gc-23@gated-at.bofh.it> (permalink) |
| References | <pxflf-8gc-5@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
3.10-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
@@ -1702,20 +1702,29 @@ 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
[PATCH 3.10 00/46] 3.10.80-stable review Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 07/46] net: socket: Fix the wrong returns for recvmsg and sendmsg Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 42/46] rtlwifi: rtl8192cu: Fix kernel deadlock Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 36/46] rt2x00: add new rt2800usb device DWA 130 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 44/46] ACPI / init: Fix the ordering of acpi_reserve_resources() Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 11/46] libceph: request a new osdmap if lingering request maps to no osd Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 19/46] ASoC: wm8960: fix "RINPUT3" audio route error Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 23/46] xhci: Solve full event ring by increasing TRBS_PER_SEGMENT to 256 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 22/46] xhci: fix isoc endpoint dequeue from advancing too far on transaction error Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 10/46] lguest: fix out-by-one error in address checking. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 31/46] mmc: atmel-mci: fix bad variable type for clkdiv Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 12/46] hwmon: (ntc_thermistor) Ensure iio channel is of type IIO_VOLTAGE Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 09/46] fs, omfs: add NULL terminator in the end up the token list Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 15/46] ALSA: hda - Add Conexant codecs CX20721, CX20722, CX20723 and CX20724 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 16/46] ALSA: hda - Add headphone quirk for Lifebook E752 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 14/46] d_walk() might skip too much Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 43/46] Input: elantech - fix semi-mt protocol for v3 HW Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 46/46] fs/binfmt_elf.c:load_elf_binary(): return -EINVAL on zero-length mappings Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 24/46] xhci: gracefully handle xhci_irq dead device Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 01/46] staging: wlags49_h2: fix extern inline functions Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 37/46] crypto: s390/ghash - Fix incorrect ghash icv buffer handling. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 08/46] KVM: MMU: fix CR4.SMEP=1, CR0.WP=0 with shadow pages Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 45/46] vfs: read file_handle only once in handle_to_path Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 06/46] kernel: use the gnu89 standard explicitly Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 18/46] ASoC: uda1380: Avoid accessing i2c bus when codec is disabled Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 13:50 +0200 [PATCH 3.10 34/46] libata: Add helper to determine when PHY events should be ignored Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 25/46] USB: visor: Match I330 phone more precisely Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 20/46] ASoC: wm8994: correct BCLK DIV 348 to 384 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 04/46] staging: rtl8712, rtl8712: avoid lots of build warnings Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 32/46] ext4: convert write_begin methods to stable_page_writes semantics Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 30/46] powerpc: Align TOC to 256 bytes Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 13/46] lib: Fix strnlen_user() to not touch memory after specified maximum Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 39/46] ARM: fix missing syscall trace exit Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 05/46] staging, rtl8192e, LLVMLinux: Remove unused inline prototype Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 03/46] staging, rtl8192e, LLVMLinux: Change extern inline to static inline Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 17/46] ASoC: mc13783: Fix wrong mask value used in mc13xxx_reg_rmw() calls Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 41/46] md/raid5: dont record new size if resize_stripes fails. Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 26/46] USB: pl2303: Remove support for Samsung I330 Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 29/46] usb: gadget: configfs: Fix interfaces array NULL-termination Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 33/46] ext4: check for zero length extent explicitly Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 40/46] svcrpc: fix potential GSSX_ACCEPT_SEC_CONTEXT decoding failures Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 [PATCH 3.10 27/46] USB: cp210x: add ID for KCF Technologies PRN device Greg Kroah-Hartman <gregkh@linuxfoundation.org> - 2015-06-03 14:00 +0200 Re: [PATCH 3.10 00/46] 3.10.80-stable review Shuah Khan <shuahkh@osg.samsung.com> - 2015-06-03 19:00 +0200
csiph-web