summaryrefslogtreecommitdiff
path: root/sysdep/unix
AgeCommit message (Collapse)Author
2023-01-24Merge commit '3186ffe79714a48542d5ad61a94c81216b522fd0' into thread-nextMaria Matejka
2023-01-24Merge commit '6bb992cb04926895be57dc97e7d569ea15a07db1' into thread-nextMaria Matejka
2023-01-23Merge commit '928a1cb034e6f9e8edcdd1dc07264cd703e00827' into thread-nextMaria Matejka
2023-01-23Merge commit '7fb23041a52d01754c53ba963e2282e524813364' into thread-nextMaria Matejka
2023-01-21Merge commit '1e47b9f203aaaad0fb658d40a1670f1d0437f1f8' into thread-nextMaria Matejka
2023-01-21Adding forgotten pthread.h #include in io-loop.h (breaks at openbsd 7.1)Maria Matejka
2023-01-20Fixed various build problems on FreeBSD and/or CLangMaria Matejka
2023-01-19Merge commit '140c534fb81d0e165b7d674e869c646455ed19d1' into thread-nextMaria Matejka
2023-01-19Decoupling loops from threads to allow fixed thread countMaria Matejka
On large configurations, too many threads would spawn with one thread per loop. Therefore, threads may now run multiple loops at once. The thread count is configurable and may be changed during run. All threads are spawned on startup. This change helps with memory bloating. BIRD filters need large temporary memory blocks to store their stack and also memory management keeps its hot page storage per-thread. Known bugs: * Thread autobalancing is not yet implemented. * Low latency loops are executed together with standard loops.
2023-01-19CLI closing fix when its action is run asynchronously.Maria Matejka
Some CLI actions, notably "show route", are run by queuing an event somewhere else. If the user closes the socket, in case such an action is being executed, the CLI must free the socket immediately from the error hook but the pool must remain until the asynchronous event finishes and cleans everything up.
2023-01-18Alloc: Minor cleanupsOndrej Zajicek
- Fix THP disable on old systems - Failed syscalls should use die() instead of bug() - Our printf uses %ld for s64 instead of long
2023-01-18Merge branch 'master' of https://gitlab.nic.cz/labs/birdMaria Matejka
2023-01-18Fix memory pre-allocationMaria Matejka
When BIRD has no free memory mapped, it allocates several pages in advance just to be sure that there is some memory available if needed. This hysteresis tactics works quite well to reduce memory ping-ping with kernel. Yet it had a subtle bug: this pre-allocation didn't take a memory coldlist into account, therefore requesting new pages from kernel even in cases when there were other pages available. This led to slow memory bloating. To demonstrate this behavior fast enough to be seen well, you may: * temporarily set the values in sysdep/unix/alloc.c as follows to exacerbate the issue: #define KEEP_PAGES_MAIN_MAX 4096 #define KEEP_PAGES_MAIN_MIN 1000 #define CLEANUP_PAGES_BULK 4096 * create a config file with several millions of static routes * periodically disable all static protocols and then reload config * log memory consumption This should give you a steady growth rate of about 16kB per cycle. If you don't set the values this high, the issue happens much more slowly, yet after 14 days of running, you are going to see an OOM kill. After this fix, pre-allocation uses the memory coldlist to get some hot pages and the same test as described here gets you a perfectly stable constant memory consumption (after some initial wobbling). Thanks to NIX-CZ for reporting and helping to investigate this issue. Thanks to Santiago for finding the cause in the code.
2023-01-17Alloc: Disable transparent huge pagesOndrej Zajicek
The usage pattern implemented in allocator seems to be incompatible with transparent huge pages, as memory released using madvise(MADV_DONTNEED) with regular page size and alignment does not seem to trigger demotion of huge pages back to regular pages, even when significant number of pages is released. Even if demotion is triggered when system memory is low, it still breaks memory accounting.
2023-01-12Log message before abortingMike Crute
Log message before aborting due to watchdog timeout. We have to use async-safe write to debug log, as it is done in signal handler. Minor changes from committer.
2022-12-10CLI: Fix for long-lived sessions during high loadsOndrej Zajicek
When there is a continuos stream of CLI commands, cli_get_command() always returns 1 (there is a new command). Anyway, the socket receive buffer was reset only when there was no command at all, leading to a strange behavior: after a while, the CLI receive buffer came to its end, then read() was called with zero size buffer, it returned 0 which was interpreted as EOF. The patch fixes that by resetting the buffer position after each command and moving remaining data at the beginning of buffer. Thanks to Maria Matejka for examining the bug and for the original bugfix.
2022-11-30BSD: Fix krt socket code w.r.t. rte/rta changesOndrej Zajicek
2022-11-09Conf: Make 'configure check' command restrictedOndrej Zajicek
While it does not directly change BIRD state, it can trigger reading arbitrary files and eating significant memory.
2022-11-09Conf: Free stored old config before parsing new oneOndrej Zajicek
BIRD keeps a previous (old) configuration for the purpose of undo. The existing code frees it after a new configuration is successfully parsed during reconfiguration. That causes memory usage spikes as there are temporarily three configurations (old, current, and new). The patch changes it to free the old one before parsing the new one (as user already requested a new config). The disadvantage is that undo is not available after failed reconfiguration.
2022-11-07Merge remote-tracking branch 'origin/master' into thread-nextMaria Matejka
2022-11-07Merge commit '0f2be469' into thread-nextMaria Matejka
2022-11-03Page allocator: Fixed minor bugs and added commentaryMaria Matejka
2022-11-02Memory pages are not munmapped, instead we just madvise()Maria Matejka
Memory unmapping causes slow address space fragmentation, leading in extreme cases to failing to allocate pages at all. Removing this problem by keeping all the pages allocated to us, yet calling madvise() to let kernel dispose of them. This adds a little complexity and overhead as we have to keep the pointers to the free pages, therefore to hold e.g. 1 GB of 4K pages with 8B pointers, we have to store 2 MB of data.
2022-10-12Fixed SSH known hosts checking with older versions of libsshMaria Matejka
2022-10-05Poll errors must also drop a corefile. And we shouldn't run sockets when ↵Maria Matejka
sockets have changed
2022-10-05Fixed previously untested paths in RPKIMaria Matejka
2022-10-04Merge commit '67256d50' into HEADMaria Matejka
2022-10-04Merge commit 'fb7fb674' into HEADMaria Matejka
2022-10-04Merge commit 'a32cee78' into HEADMaria Matejka
2022-10-04Merge commit '71b434a9' into HEADMaria Matejka
2022-10-04Merge commit '0072d11f' into tmp-learnMaria Matejka
2022-09-29Merge branch 'tmp-bad-learn' into thread-nextMaria Matejka
2022-09-29Merge commit '9efaf6ba' into tmp-bad-learnMaria Matejka
Also fixed forgotten best route selection among alien routes.
2022-09-27Merge commit '4364ee' into tmp-bad-learnMaria Matejka
2022-09-27Merge commit 'cae5979871ee7aa341334f8b1af6bafc60ee9692' into tmp-bad-learnMaria Matejka
2022-09-27KRT: Fix route learningMaria Matejka
This is a reimplementation of commit 0f2be469f897b6d9f925563bbf522438c83522ea by Alexander Zubkov. In the master branch, changes in commit eb937358 broke setting of channel preference for alien routes learned during scan. The preference was set only for async routes. The original solution is extended here to accomodate for v3 specifics.
2022-09-27KRT: Fix setting default preferenceAlexander Zubkov
Changes in commit eb937358 broke setting of channel preference for alien routes learned during scan. The preference was set only for async routes. Move common attribute processing part of functions krt_learn_async() and krt_learn_async() to a separate function to have only one place for such changes.
2022-09-21Local page allocationMaria Matejka
2022-09-20Pipe kick-and-drain packed into a neat structure and functions.Maria Matejka
2022-09-20Fixed display of standby memoryMaria Matejka
2022-09-18Loop flags: a simple idempotent event announcement mechanismMaria Matejka
2022-09-18Cancelling all timers when loop stopsMaria Matejka
2022-09-18Memory pages allocator is now a global simple lockless structureMaria Matejka
2022-09-09Merge commit 'd2c1036a42881d413ec97203ede92a69f8cd218f' into thread-nextMaria Matejka
2022-09-08Table access is now locked.Maria Matejka
2022-08-18Simplified the protocol hookup code in MakefilesMaria Matejka
2022-08-05Merge commit '534d0a4b' into thread-nextMaria Matejka
2022-08-02Merge commit 'f0507f05ce57398e135651896dace4cb68eeed54' into thread-nextMaria Matejka
2022-08-02Introducing basic RCU primitives for lock-less shared data structuresMaria Matejka
2022-07-28Moved the thread starting code to IO loop codeMaria Matejka