| Commit message (Collapse) | Author | Files | Lines | ||
|---|---|---|---|---|---|
| 2008-10-13 | osd: lossy send policy on acks | Sage Weil | 1 | -3/+2 | |
| 2008-10-13 | objecter: kick requests when we detect a remote session reset | Sage Weil | 4 | -28/+37 | |
| 2008-10-13 | msgr: handle incoming lossy connection when outgoing policy is lossless | Sage Weil | 1 | -0/+13 | |
| Basically, try to wake up our lossless connection. The lossy attempt never survives. This avoids worrying about keeping session state alive (connect_seq, etc.). | |||||
| 2008-10-13 | msgr: track lossy mode independently for self, peer | Sage Weil | 11 | -59/+161 | |
| The policy will be asymmetrical for the OSDs, so we need to track it independently. The various assertions aren't all worked out yet. Notably, connection races aren't quite right. But the basic bits are there. | |||||
| 2008-10-13 | client: fix && || parens | Sage Weil | 1 | -1/+1 | |
| 2008-10-13 | filestore: use BTRFS_IOC_SYNC instead of fsync | Sage Weil | 1 | -1/+7 | |
| fsync() won't do the right thing on newer versions of btrfs, due do the new tree log stuff. Use the SYNC ioctl. | |||||
| 2008-10-13 | filestore: detect new btrfs ioctls | Sage Weil | 2 | -4/+22 | |
| Don't use them yet, though. | |||||
| 2008-10-13 | fix of crc32c calculation | Yehuda Sadeh | 1 | -6/+4 | |
| 2008-10-11 | replace the crc32c code | Yehuda Sadeh | 4 | -128/+737 | |
| 2008-10-09 | debian: changelog update | Sage Weil | 1 | -1/+6 | |
| 2008-10-09 | debian: fix debian-doc; include debian dir in dist tarball | Sage Weil | 3 | -4/+2 | |
| 2008-10-09 | mon: populate last_beacon properly for mds liveness check | Sage Weil | 1 | -17/+17 | |
| It was only populating on paxos updates, but that missed the case where the leader moves from one monitor to another (live) peon, who has an empty last_beacon. Move it where it makes the most sense. | |||||
| 2008-10-09 | debian: tweak ceph-doc paths | Sage Weil | 2 | -1/+2 | |
| 2008-10-09 | dstart.sh: replace dstartnew.sh | Sage Weil | 3 | -73/+96 | |
| -n will create new fs, otherwise it will start up using existing data. | |||||
| 2008-10-09 | filestore: fix collection attrs | Sage Weil | 2 | -22/+33 | |
| Need to prepend user.ceph. to attr names... | |||||
| 2008-10-09 | todos | Sage Weil | 1 | -5/+9 | |
| 2008-10-09 | mon: include pg usage stats, header in pg dump | Sage Weil | 1 | -6/+12 | |
| 2008-10-09 | debian: move map tools and crun to ceph-common | Sage Weil | 9 | -12/+17 | |
| 2008-10-08 | osd: account for used kb separately | Sage Weil | 4 | -10/+21 | |
| Account for used separately from available, as the underlying fs may do tricks reserving space for root and such. | |||||
| 2008-10-08 | osd: use kb instead of blocks for pg, osd utilization | Sage Weil | 6 | -38/+41 | |
| 2008-10-08 | osd: prioritize heartbeat messages | Sage Weil | 1 | -2/+3 | |
| 2008-10-08 | msgr: include priority in msg header, make dispatch a priority queue | Sage Weil | 7 | -59/+76 | |
| Generalizes previous hack that put messages from the monitor at the front of the dispatch queue. Monitor now just sets a (non-default) default_send_priority of CEPH_MSG_PRIO_HIGH. That value is used only if the message priority isn't set explicitly by set_priority() before being queued for send. | |||||
| 2008-10-08 | journal: protect journal access (namely, completions) with mutex | Sage Weil | 1 | -0/+9 | |
| The commit_waiters map was getting corrupted occasionally. | |||||
| 2008-10-08 | debian: include crun in osd, mds, mon packages | Sage Weil | 3 | -0/+4 | |
| 2008-10-08 | osdmaptool: fix silly num_dom bug | Sage Weil | 1 | -1/+1 | |
| 2008-10-08 | ceph.spec.in: include crun | Erwin, Brock A | 1 | -1/+2 | |
| 2008-10-07 | kclient: initializing kaddr (merge fix)v0.4 | Yehuda Sadeh | 2 | -2/+7 | |
| 2008-10-07 | kclient: use both writepage and crc | Yehuda Sadeh | 1 | -26/+5 | |
| 2008-10-07 | kclient: disabling the readpage | Yehuda Sadeh | 1 | -3/+6 | |
| 2008-10-07 | kclient: disabling readpage | Yehuda Sadeh | 1 | -1/+1 | |
| 2008-10-07 | kclient: use writepage instead of sendmsg for some of the data | Yehuda Sadeh | 1 | -2/+35 | |
| 2008-10-07 | kclient: missing include file | Yehuda Sadeh | 1 | -0/+1 | |
| 2008-10-07 | Revert "kclient: use writepage instead of sendmsg for some of the data" | Yehuda Sadeh | 1 | -35/+2 | |
| This reverts commit 406fc33a6bb6120925edda0db9fc5f624d43efb9. | |||||
| 2008-10-07 | kclient: use writepage instead of sendmsg for some of the data | Yehuda Sadeh | 1 | -2/+35 | |
| 2008-10-07 | msgr: expand footer flags, include nocrc, kclient nocrc mount option | Sage Weil | 6 | -26/+44 | |
| 2008-10-07 | ebofs: -ENOSPC in apply_transaction | Sage Weil | 2 | -0/+16 | |
| 2008-10-07 | kclient: change default rsize to 128k | Yehuda Sadeh | 2 | -3/+3 | |
| 2008-10-07 | kclient: use both writepage and crc | Yehuda Sadeh | 1 | -26/+5 | |
| 2008-10-07 | kclient: disabling the readpage | Yehuda Sadeh | 1 | -3/+6 | |
| 2008-10-07 | kclient: disabling readpage | Yehuda Sadeh | 1 | -1/+1 | |
| 2008-10-07 | kclient: use writepage instead of sendmsg for some of the data | Yehuda Sadeh | 1 | -2/+35 | |
| 2008-10-07 | kclient: small fix take two | Yehuda Sadeh | 1 | -2/+4 | |
| 2008-10-07 | kclient: small fix for bdi | Yehuda Sadeh | 1 | -1/+1 | |
| 2008-10-07 | kclient: use a private bdi | Yehuda Sadeh | 3 | -0/+37 | |
| 2008-10-07 | kclient: fix file to object mapping | Sage Weil | 3 | -34/+29 | |
| We ignore cases where the stripe_unit is small, for now, as that will require passing a stride size back to the caller so that the correctly spaced pages are used. | |||||
| 2008-10-06 | crushtool: verify explicit item pos | Sage Weil | 1 | -0/+4 | |
| 2008-10-06 | cm.txt: fix up metaroot pool | Sage Weil | 1 | -3/+3 | |
| 2008-10-06 | crushtool: verify item pos | Sage Weil | 2 | -12/+16 | |
| 2008-10-06 | dstartnew.sh: use custom crush map with separate metadata osd pool | Sage Weil | 5 | -16/+132 | |
| 2008-10-06 | crush: fix grammar | Sage Weil | 1 | -1/+1 | |
 |
index : ceph | |
| ceph | Fast-forward packages |
| summaryrefslogtreecommitdiffstats |