summaryrefslogtreecommitdiff
path: root/logger.c
Commit message (Collapse)AuthorAgeFilesLines
* restartable cachedormando2019-09-171-12/+22
| | | | | | | | | | | | | | | "-e /path/to/tmpfsmnt/file" SIGUSR1 for graceful stop restart requires the same memory limit, slab sizes, and some other infrequently changed details. Most other options and features can change between restarts. Binary can be upgraded between restarts. Restart does some fixup work on start for every item in cache. Can take over a minute with more than a few hundred million items in cache. Keep in mind when a cache is down it may be missing invalidations, updates, and so on.
* log client connection id with fetchers and mutationsTharanga Gamaethige2019-08-271-9/+12
| | | | you can now monitor fetch and mutations of a given client
* Fix off-by-one in logger to allow CAS commands to be logged.Andrew Drake2019-08-271-1/+1
|
* Use correct buffer size for internal URI encoding.Tharanga Gamaethige2019-05-201-8/+8
| | | | | Modified Logger and Crawler to use the correct buffer length when they are printing URI encoded keys. Fixes #471
* fix compile error on centos7dormando2019-04-271-0/+1
| | | | I have no idea why this worked without the include? fixes #478
* Basic implementation of TLS for memcached.1.5.13Tharanga Gamaethige2019-04-151-2/+2
| | | | | | | | | | | | | Most of the work done by Tharanga. Some commits squashed in by dormando. Also reviewed by dormando. Tested, working, but experimental implementation of TLS for memcached. Enable with ./configure --enable-tls Requires OpenSSL 1.1.0 or better. See `memcached -h` output for usage.
* add missing va_end() call to logger_log()Miroslav Lichvar2018-07-111-0/+1
|
* Fix SIGBUS from alignment issues on 64bit ARMdormando2018-03-151-3/+11
| | | | | | | | | | | ARMv8 (and in general aarch64) has flipped some strictness requirements. However, at some point in history the NEED_ALIGN configure check code was optimized away by GCC. This fixes detection of alignment, as well as fixes an unaligned access that snuck in via the logging code. Also fixes a 64bit GCC atomics test that possibly never worked before.
* extstore: add evictions-related write logsdormando2017-12-151-1/+45
| | | | | | "watch evictions" will show a stream of evictions + writes to extstore. useful for analyzing the remaining ttl or key pattern of stuff being flushed.
* extstore: skip unhit objects if full in compactiondormando2017-11-281-1/+1
| | | | | | if < 2 free pages left, "evict" objects which haven't been hit at all. should be better than evicting everything if we can continue compacting.
* external storage base commitdormando2017-11-281-1/+21
| | | | | been squashing reorganizing, and pulling code off to go upstream ahead of merging the whole branch.
* make for loop more clear in logger watcherdormando2017-10-291-1/+1
| | | | | | | This wasn't a bug, but add -1 here makes it more clear. The function will early exit in any cases where it would've overflowed here. thanks to shqking on github for the report
* add a real slab automover algorithmdormando2017-06-231-0/+3
| | | | converts the python script to C, more or less.
* LRU crawler scheduling improvementsdormando2017-05-291-1/+1
| | | | | | | | | | | | | | | | | | | when trying to manually run a crawl, the internal autocrawler is now blocked from restarting for 60 seconds. the internal autocrawl now independently schedules LRU's, and can re-schedule sub-LRU's while others are still running. should allow much better memory control when some sub-lru's (such as TEMP or WARM) are small, or slab classes are differently sized. this also makes the crawler drop its lock frequently.. this fixes an issue where a long crawl happening at the same time as a hash table expansion could hang the server until the crawl finished. to improve still: - elapsed time can be wrong in the logger entry - need to cap number of entries scanned. enough set pressure and a crawl may never finish.
* Sleep more aggressively in some threadsGrant Mathews2017-05-221-5/+9
| | | | | | | | | | | The logger and lru maintainer threads both adjust how long they sleep based on how busy they are. This adjustment should be exponential, to more quickly adjust to workloads. The logger thread in particular would only adjust 50 microseconds at a time, and was capped at 100 milliseconds of sleep, causing many unnecessary wakeups on an otherwise idle dev machine. Adjust this cap to 1 second.
* log class id with fetchers and mutationsdormando2017-01-041-11/+17
| | | | you can now cross-reference slab classes of evicted prefixes with misses
* fix store log and add ttldormando2017-01-041-6/+12
| | | | | the TTL is relative so you won't see the exact TTL on entry. Also fixes two off-by-one's for the status values.
* tune crawler logger, fix crawler watermarkdormando2016-12-301-1/+1
| | | | | should be looking for 1% of potential reclaims, not 1% of all the items it saw. Otherwise could be wedged into doing nothing.
* add logging endpoint for LRU crawlerdormando2016-12-301-1/+4
| | | | for the internal checker, primarily.
* stop pushing NULl byte into watcher streamdormando2016-12-271-4/+6
| | | | also fixes logger L_DEBUG prints.
* Missing necessary header for atomic_inc_64_nv() used in logger.cAlexander Pyhalov2016-12-191-0/+4
|
* make logger use uriencode out of util.cdormando2016-08-191-39/+3
|
* don't fail on systems without 64bit atomicsdormando2016-07-011-2/+2
| | | | | | | | | We only explicitly tested for short atomics. Then I added 8byte atomic usage in the logger: now separately test for those.. since some systems can have one but not the other, I'd rather use atomics where available then fall back to a mutex when necessary. Reproduced this on a raspberry pi 2.
* split up logger_thread_parse_entrydormando2016-07-011-57/+76
| | | | | | now a main function + helpers, with a separate write function. drives me a lot less crazy now.
* first refactor of logger_thread_parse_entrydormando2016-07-011-94/+46
| | | | | | Was in a working state for release, now doing some work to clean up the routine. Is much shorter and clearer now. Function needs to be split into several functions from here.
* add -o watcher_logbuf_size=N worker_logbuf_size=Ndormando2016-06-231-2/+2
| | | | | | | the defaults should just about always be used, but this is now tunable for completeness. Also handy for writing tests. This also hopefully makes the watcher.t test not flaky anymore.
* add #include <stdio.h> to fix error: implicit declaration of function ↵Mathieu CARBONNEAUX2016-06-201-0/+1
| | | | ‘snprintf’
* add protocol documentation1.4.26dormando2016-06-171-0/+1
| | | | and a note for missing information.
* misc cleanups for logger code.dormando2016-06-171-6/+4
| | | | tests pass now.
* logger endpoints for first releasedormando2016-06-161-1/+118
| | | | | | | | | | | swapping "RAWCMDS" for internal hooks on when items are fetched or stored. This doesn't map 1:1 with commands, ie: a store is internally a fetch then store, so two log lines are generated. An ascii multiget one make one log line per key fetched. It's a good place to start. Need to come back and refactor parts of logger.c again, then convert all prints in the codebase to log entries.
* convert eviction log to new processdormando2016-06-161-24/+37
| | | | | | | | | | | | add LOGGER_LOG() macro wrapper for callers. eviction logging is now using the "more final" method, where data is copied into structs embedded into the per-worker circular buffer. This moves the expensive snprintf calls to the background thread, and also allows making the logging format switchable. also switched the format to key=value. it's still largely readable but much easier to parse.
* logger: add a uri encoder for printing keysdormando2016-06-161-2/+38
| | | | makes a map on start of bgthread to speed up conversion a little.
* small logger code clarity improvementsdormando2016-06-161-34/+48
| | | | | | | put header sections for utils/bgthread/api, edit function names slightly so it's clear what's only called from the bgthread. remaining FIXME/TODO's appear noncritical. might do those in the future.
* some global stats for bg loggerdormando2016-06-161-17/+42
| | | | | four obvious ones. have a handy place to do the summarization when the logger wakes up for its run, avoiding the locks.
* improve 'watch' command processing a littledormando2016-06-161-0/+1
| | | | | moves to its own function, respods "OK\r\n" to client, allows multiple arguments for multiple flags. Needs more thought before adding sampling.
* poll() smarter when full, print skipped countdormando2016-06-161-29/+52
| | | | | | | | | When lines are skipped to a watcher, a [skipped: n] is printed before resuming. Also polls full watcher directly once, and will wait until the outer loop to re-poll. Think the routine can be simplified... it works so will leave it and revisit later.
* use one bipbuffer per watcher. remove iovec code.dormando2016-06-161-205/+75
| | | | | | | | | | | | | after the previous commit's exercise, this greatly simplifies the writing process. The buffers are large but can be tuned with performance testing. Lines are now rendered into scratch space, and if event flags (eflags) match for a watcher, copy the bytes into that watcher's specific buffer. In most realistic cases, watchers will be watching different streams of information. While this does require a minimum of one memcpy instead of directly writing into the bipbuf as before, it removes all of the loops and management of iovecs required for filtering events on the write-to-socket end.
* remove "logger chunks", add individualized streamsdormando2016-06-161-136/+170
| | | | | | | | | | | | | | | | | | | Stop doing a multi-reader circular buffer structure on top of a circular buffer. Also adds individualized streams based off of the central buffer. Sadly this requires managing iovecs and dealing with partial writes into said iovecs. That makes things very complicated. Since it's not clear to me how to simplify it too much (as of this writing), one of the next commits should remove iovecs and instead give each watcher its own circular buffer. The parser thread will copy watched events into each buffer. The above would only be slower for the case of many watchers watching the same event streams. Given all of the extra loops required for managing the iovecs, and the more complicated syscall handling, it might even be the same speed to manage multiple buffers anyway. I completed this intermediary change since it simplifies the surrounding code and was educational to fiddle with iovecs again.
* switch from bit fields to bit manipulationdormando2016-06-161-21/+8
| | | | can't compare bit fields en-masse, which makes things too difficult.
* manage logger watcher flags.dormando2016-06-161-6/+44
| | | | | very temporary user control. allows to watch either fetchers or evictions, but not both, and always with timestamps.
* initial logger code.dormando2016-06-161-0/+637
Logs are written to per-thread buffers. A new background thread aggregates the logs, further processes them, then writes them to any "watchers". Logs can have the time added to them, and all have a GID so they can be put back into strict order. This is an early preview. Code needs refactoring and a more complete set of options. All watchers are also stuck viewing the global feed of logs, even if they asked for different data. As of this commit there's no way to toggle the "stderr" watcher.
View Lorry Controller Status