| Commit message (Expand) | Author | Age | Files | Lines |
* | MFC r257155, r257582, r259191, r259192, r259193, r259194, r259195, r259196: | trociny | 2013-12-28 | 1 | -5/+19 |
* | Fix comments. | trociny | 2013-09-19 | 1 | -3/+2 |
* | Use cv_broadcast() instead of cv_signal() when waking up threads | trociny | 2013-09-19 | 1 | -1/+1 |
* | Delete requests can be larger than MAXPHYS. | pjd | 2013-03-14 | 1 | -1/+1 |
* | Add i/o error counters to hastd(8) and make hastctl(8) display | trociny | 2013-02-25 | 1 | -1/+17 |
* | - Add support for 'memsync' mode. This is the fastest replication mode that's | pjd | 2013-02-17 | 1 | -2/+46 |
* | Style cleanups. | pjd | 2012-01-13 | 1 | -6/+11 |
* | For functions that return -1 on failure check exactly for -1 and not for | pjd | 2012-01-10 | 1 | -16/+16 |
* | fork(2) returns -1 on failure, not some random negative number. | pjd | 2012-01-06 | 1 | -1/+1 |
* | Remove redundant assignment. | pjd | 2011-12-15 | 1 | -2/+0 |
* | Remove redundant space. | pjd | 2011-10-27 | 1 | -1/+1 |
* | - Eliminate the need for hio_nv. | pjd | 2011-10-27 | 1 | -25/+55 |
* | Correct comments. | pjd | 2011-10-27 | 1 | -3/+3 |
* | If the underlying provider doesn't support BIO_FLUSH, log it only once | pjd | 2011-09-28 | 1 | -4/+14 |
* | Break a bit earlier. | pjd | 2011-09-28 | 1 | -0/+1 |
* | Prefer PJDLOG_ASSERT() and PJDLOG_ABORT() over assert() and abort(). | pjd | 2011-09-27 | 1 | -2/+2 |
* | In HAST we use two sockets - one for only sending the data and one for | trociny | 2011-06-17 | 1 | -0/+4 |
* | Keep statistics on number of BIO_READ, BIO_WRITE, BIO_DELETE and BIO_FLUSH | pjd | 2011-05-23 | 1 | -0/+14 |
* | Recognize HIO_FLUSH requests. | pjd | 2011-05-21 | 1 | -0/+1 |
* | Currently we are unable to use capsicum for the primary worker process, | pjd | 2011-05-14 | 1 | -1/+1 |
* | Scenario: | pjd | 2011-04-19 | 1 | -0/+1 |
* | Declare directions for sockets between primary and secondary. | pjd | 2011-04-02 | 1 | -0/+7 |
* | Add mapsize to the header just before sending the packet. | pjd | 2011-03-25 | 1 | -1/+1 |
* | Use role2str() when setting process title. | pjd | 2011-03-25 | 1 | -1/+1 |
* | Don't create socketpair for connection forwarding between parent and secondary. | pjd | 2011-03-23 | 1 | -12/+0 |
* | White space cleanups. | pjd | 2011-03-22 | 1 | -2/+2 |
* | When dropping privileges prefer capsicum over chroot+setgid+setuid. | pjd | 2011-03-21 | 1 | -1/+1 |
* | Fix typo. | pjd | 2011-03-21 | 1 | -1/+1 |
* | Be pedantic and free nvout before exiting. | pjd | 2011-03-21 | 1 | -0/+1 |
* | Detect situation where resource internal identifier differs. | pjd | 2011-03-21 | 1 | -0/+13 |
* | In hast.conf we define the other node's address in 'remote' variable. | pjd | 2011-03-21 | 1 | -3/+3 |
* | For secondary, set 2 * HAST_KEEPALIVE seconds timeout for incoming | trociny | 2011-03-17 | 1 | -1/+1 |
* | Make workers inherit debug level from the main process. | trociny | 2011-03-11 | 1 | -1/+3 |
* | Setup another socketpair between parent and child, so that primary sandboxed | pjd | 2011-02-03 | 1 | -0/+12 |
* | Let the caller log info about successful privilege drop. | pjd | 2011-02-03 | 1 | -0/+1 |
* | - Use pjdlog for assertions and aborts as this will log assert/abort message | pjd | 2011-01-31 | 1 | -7/+6 |
* | Drop privileges in worker processes. | pjd | 2011-01-28 | 1 | -0/+3 |
* | Use newly added descriptors_assert() function to ensure only expected | pjd | 2011-01-28 | 1 | -0/+2 |
* | Close all unneeded descriptors after fork(2). | pjd | 2011-01-28 | 1 | -6/+11 |
* | Before this change on first connect between primary and secondary we | pjd | 2010-10-24 | 1 | -2/+11 |
* | Simplify code a bit. | pjd | 2010-10-24 | 1 | -3/+1 |
* | Plug memory leak. | pjd | 2010-10-24 | 1 | -0/+2 |
* | Switch to sigprocmask(2) API also in the main process and secondary process. | pjd | 2010-09-22 | 1 | -2/+4 |
* | Fix possible deadlock where worker process sends an event to the main process | pjd | 2010-09-22 | 1 | -4/+14 |
* | Add __dead2 to functions that we know they are going to exit. | pjd | 2010-09-20 | 1 | -1/+1 |
* | Correct error message. | pjd | 2010-08-31 | 1 | -1/+1 |
* | Because it is very hard to make fork(2) from threaded process safe (we are | pjd | 2010-08-30 | 1 | -4/+17 |
* | Execute hook when connection between the nodes is established or lost. | pjd | 2010-08-30 | 1 | -3/+21 |
* | Execute hook when split-brain is detected. | pjd | 2010-08-30 | 1 | -0/+2 |
* | Allow to run hooks from the main hastd process. | pjd | 2010-08-29 | 1 | -0/+3 |