Permalink
Commits on Oct 11, 2011
-
Fix powerpc compile warnings mm/page-writeback.c: In function 'bdi_position_ratio': mm/page-writeback.c:622:3: warning: comparison of distinct pointer types lacks a cast [enabled by default] page-writeback.c:635:4: warning: comparison of distinct pointer types lacks a cast [enabled by default] Also fix gcc "uninitialized var" warnings. Reported-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Commits on Oct 3, 2011
-
One thing puzzled me is that in JBOD case, the per-disk writeout performance is smaller than the corresponding single-disk case even when they have comparable bdi_thresh. Tracing shows find that in single disk case, bdi_writeback is always kept high while in JBOD case, it could drop low from time to time and correspondingly bdi_reclaimable could sometimes rush high. The fix is to watch bdi_reclaimable and kick background writeback as soon as it goes high. This resembles the global background threshold but in per-bdi manner. The trick is, as long as bdi_reclaimable does not go high, bdi_writeback naturally won't go low because bdi_reclaimable+bdi_writeback ~= bdi_thresh. With less fluctuated writeback pages, JBOD performance is observed to increase noticeably in various cases. vmstat:nr_written values before/after patch: 3.1.0-rc4-wo-underrun+ 3.1.0-rc4-bgthresh3+ ------------------------ ------------------------ 125596480 +25.9% 158179363 JBOD-10HDD-16G/ext4-100dd-1M-24p-16384M-20:10-X 61790815 +110.4% 130032231 JBOD-10HDD-16G/ext4-10dd-1M-24p-16384M-20:10-X 58853546 -0.1% 58823828 JBOD-10HDD-16G/ext4-1dd-1M-24p-16384M-20:10-X 110159811 +24.7% 137355377 JBOD-10HDD-16G/xfs-100dd-1M-24p-16384M-20:10-X 69544762 +10.8% 77080047 JBOD-10HDD-16G/xfs-10dd-1M-24p-16384M-20:10-X 50644862 +0.5% 50890006 JBOD-10HDD-16G/xfs-1dd-1M-24p-16384M-20:10-X 42677090 +28.0% 54643527 JBOD-10HDD-thresh=100M/ext4-100dd-1M-24p-16384M-100M:10-X 47491324 +13.3% 53785605 JBOD-10HDD-thresh=100M/ext4-10dd-1M-24p-16384M-100M:10-X 52548986 +0.9% 53001031 JBOD-10HDD-thresh=100M/ext4-1dd-1M-24p-16384M-100M:10-X 26783091 +36.8% 36650248 JBOD-10HDD-thresh=100M/xfs-100dd-1M-24p-16384M-100M:10-X 35526347 +14.0% 40492312 JBOD-10HDD-thresh=100M/xfs-10dd-1M-24p-16384M-100M:10-X 44670723 -1.1% 44177606 JBOD-10HDD-thresh=100M/xfs-1dd-1M-24p-16384M-100M:10-X 127996037 +22.4% 156719990 JBOD-10HDD-thresh=2G/ext4-100dd-1M-24p-16384M-2048M:10-X 57518856 +3.8% 59677625 JBOD-10HDD-thresh=2G/ext4-10dd-1M-24p-16384M-2048M:10-X 51919909 +12.2% 58269894 JBOD-10HDD-thresh=2G/ext4-1dd-1M-24p-16384M-2048M:10-X 86410514 +79.0% 154660433 JBOD-10HDD-thresh=2G/xfs-100dd-1M-24p-16384M-2048M:10-X 40132519 +38.6% 55617893 JBOD-10HDD-thresh=2G/xfs-10dd-1M-24p-16384M-2048M:10-X 48423248 +7.5% 52042927 JBOD-10HDD-thresh=2G/xfs-1dd-1M-24p-16384M-2048M:10-X 206041046 +44.1% 296846536 JBOD-10HDD-thresh=4G/xfs-100dd-1M-24p-16384M-4096M:10-X 72312903 -19.4% 58272885 JBOD-10HDD-thresh=4G/xfs-10dd-1M-24p-16384M-4096M:10-X 50635672 -0.5% 50384787 JBOD-10HDD-thresh=4G/xfs-1dd-1M-24p-16384M-4096M:10-X 68308534 +115.7% 147324758 JBOD-10HDD-thresh=800M/ext4-100dd-1M-24p-16384M-800M:10-X 57882933 +14.5% 66269621 JBOD-10HDD-thresh=800M/ext4-10dd-1M-24p-16384M-800M:10-X 52183472 +12.8% 58855181 JBOD-10HDD-thresh=800M/ext4-1dd-1M-24p-16384M-800M:10-X 53788956 +94.2% 104460352 JBOD-10HDD-thresh=800M/xfs-100dd-1M-24p-16384M-800M:10-X 44493342 +35.5% 60298210 JBOD-10HDD-thresh=800M/xfs-10dd-1M-24p-16384M-800M:10-X 42641209 +18.9% 50681038 JBOD-10HDD-thresh=800M/xfs-1dd-1M-24p-16384M-800M:10-X Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> -
Keep a minimal pool of dirty pages for each bdi, so that the disk IO queues won't underrun. Also gently increase a small bdi_thresh to avoid it stuck in 0 for some light dirtied bdi. It's particularly useful for JBOD and small memory system. It may result in (pos_ratio > 1) at the setpoint and push the dirty pages high. This is more or less intended because the bdi is in the danger of IO queue underflow. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
-
The dirty pause time shall ultimately be controlled by adjusting nr_dirtied_pause, since there is relationship pause = pages_dirtied / task_ratelimit Assuming pages_dirtied ~= nr_dirtied_pause task_ratelimit ~= dirty_ratelimit We get nr_dirtied_pause ~= dirty_ratelimit * desired_pause Here dirty_ratelimit is preferred over task_ratelimit because it's more stable. It's also important to limit possible large transitional errors: - bw is changing quickly - pages_dirtied << nr_dirtied_pause on entering dirty exceeded area - pages_dirtied >> nr_dirtied_pause on btrfs (to be improved by a separate fix, but still expect non-trivial errors) So we end up using the above formula inside clamp_val(). The best test case for this code is to run 100 "dd bs=4M" tasks on btrfs and check its pause time distribution. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
-
Apply two policies to scale down the max pause time for 1) small number of concurrent dirtiers 2) small memory system (comparing to storage bandwidth) MAX_PAUSE=200ms may only be suitable for high end servers with lots of concurrent dirtiers, where the large pause time can reduce much overheads. Otherwise, smaller pause time is desirable whenever possible, so as to get good responsiveness and smooth user experiences. It's actually required for good disk utilization in the case when all the dirty pages can be synced to disk within MAX_PAUSE=200ms. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
-
As proposed by Chris, Dave and Jan, don't start foreground writeback IO inside balance_dirty_pages(). Instead, simply let it idle sleep for some time to throttle the dirtying task. In the mean while, kick off the per-bdi flusher thread to do background writeback IO. RATIONALS ========= - disk seeks on concurrent writeback of multiple inodes (Dave Chinner) If every thread doing writes and being throttled start foreground writeback, it leads to N IO submitters from at least N different inodes at the same time, end up with N different sets of IO being issued with potentially zero locality to each other, resulting in much lower elevator sort/merge efficiency and hence we seek the disk all over the place to service the different sets of IO. OTOH, if there is only one submission thread, it doesn't jump between inodes in the same way when congestion clears - it keeps writing to the same inode, resulting in large related chunks of sequential IOs being issued to the disk. This is more efficient than the above foreground writeback because the elevator works better and the disk seeks less. - lock contention and cache bouncing on concurrent IO submitters (Dave Chinner) With this patchset, the fs_mark benchmark on a 12-drive software RAID0 goes from CPU bound to IO bound, freeing "3-4 CPUs worth of spinlock contention". * "CPU usage has dropped by ~55%", "it certainly appears that most of the CPU time saving comes from the removal of contention on the inode_wb_list_lock" (IMHO at least 10% comes from the reduction of cacheline bouncing, because the new code is able to call much less frequently into balance_dirty_pages() and hence access the global page states) * the user space "App overhead" is reduced by 20%, by avoiding the cacheline pollution by the complex writeback code path * "for a ~5% throughput reduction", "the number of write IOs have dropped by ~25%", and the elapsed time reduced from 41:42.17 to 40:53.23. * On a simple test of 100 dd, it reduces the CPU %system time from 30% to 3%, and improves IO throughput from 38MB/s to 42MB/s. - IO size too small for fast arrays and too large for slow USB sticks The write_chunk used by current balance_dirty_pages() cannot be directly set to some large value (eg. 128MB) for better IO efficiency. Because it could lead to more than 1 second user perceivable stalls. Even the current 4MB write size may be too large for slow USB sticks. The fact that balance_dirty_pages() starts IO on itself couples the IO size to wait time, which makes it hard to do suitable IO size while keeping the wait time under control. Now it's possible to increase writeback chunk size proportional to the disk bandwidth. In a simple test of 50 dd's on XFS, 1-HDD, 3GB ram, the larger writeback size dramatically reduces the seek count to 1/10 (far beyond my expectation) and improves the write throughput by 24%. - long block time in balance_dirty_pages() hurts desktop responsiveness Many of us may have the experience: it often takes a couple of seconds or even long time to stop a heavy writing dd/cp/tar command with Ctrl-C or "kill -9". - IO pipeline broken by bumpy write() progress There are a broad class of "loop {read(buf); write(buf);}" applications whose read() pipeline will be under-utilized or even come to a stop if the write()s have long latencies _or_ don't progress in a constant rate. The current threshold based throttling inherently transfers the large low level IO completion fluctuations to bumpy application write()s, and further deteriorates with increasing number of dirtiers and/or bdi's. For example, when doing 50 dd's + 1 remote rsync to an XFS partition, the rsync progresses very bumpy in legacy kernel, and throughput is improved by 67% by this patchset. (plus the larger write chunk size, it will be 93% speedup). The new rate based throttling can support 1000+ dd's with excellent smoothness, low latency and low overheads. For the above reasons, it's much better to do IO-less and low latency pauses in balance_dirty_pages(). Jan Kara, Dave Chinner and me explored the scheme to let balance_dirty_pages() wait for enough writeback IO completions to safeguard the dirty limit. However it's found to have two problems: - in large NUMA systems, the per-cpu counters may have big accounting errors, leading to big throttle wait time and jitters. - NFS may kill large amount of unstable pages with one single COMMIT. Because NFS server serves COMMIT with expensive fsync() IOs, it is desirable to delay and reduce the number of COMMITs. So it's not likely to optimize away such kind of bursty IO completions, and the resulted large (and tiny) stall times in IO completion based throttling. So here is a pause time oriented approach, which tries to control the pause time in each balance_dirty_pages() invocations, by controlling the number of pages dirtied before calling balance_dirty_pages(), for smooth and efficient dirty throttling: - avoid useless (eg. zero pause time) balance_dirty_pages() calls - avoid too small pause time (less than 4ms, which burns CPU power) - avoid too large pause time (more than 200ms, which hurts responsiveness) - avoid big fluctuations of pause times It can control pause times at will. The default policy (in a followup patch) will be to do ~10ms pauses in 1-dd case, and increase to ~100ms in 1000-dd case. BEHAVIOR CHANGE =============== (1) dirty threshold Users will notice that the applications will get throttled once crossing the global (background + dirty)/2=15% threshold, and then balanced around 17.5%. Before patch, the behavior is to just throttle it at 20% dirtyable memory in 1-dd case. Since the task will be soft throttled earlier than before, it may be perceived by end users as performance "slow down" if his application happens to dirty more than 15% dirtyable memory. (2) smoothness/responsiveness Users will notice a more responsive system during heavy writeback. "killall dd" will take effect instantly. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> -
Add two fields to task_struct. 1) account dirtied pages in the individual tasks, for accuracy 2) per-task balance_dirty_pages() call intervals, for flexibility The balance_dirty_pages() call interval (ie. nr_dirtied_pause) will scale near-sqrt to the safety gap between dirty pages and threshold. The main problem of per-task nr_dirtied is, if 1k+ tasks start dirtying pages at exactly the same time, each task will be assigned a large initial nr_dirtied_pause, so that the dirty threshold will be exceeded long before each task reached its nr_dirtied_pause and hence call balance_dirty_pages(). The solution is to watch for the number of pages dirtied on each CPU in between the calls into balance_dirty_pages(). If it exceeds ratelimit_pages (3% dirty threshold), force call balance_dirty_pages() for a chance to set bdi->dirty_exceeded. In normal situations, this safeguarding condition is not expected to trigger at all. On the sqrt in dirty_poll_interval(): It will serve as an initial guess when dirty pages are still in the freerun area. When dirty pages are floating inside the dirty control scope [freerun, limit], a followup patch will use some refined dirty poll interval to get the desired pause time. thresh-dirty (MB) sqrt 1 16 2 22 4 32 8 45 16 64 32 90 64 128 128 181 256 256 512 362 1024 512 The above table means, given 1MB (or 1GB) gap and the dd tasks polling balance_dirty_pages() on every 16 (or 512) pages, the dirty limit won't be exceeded as long as there are less than 16 (or 512) concurrent dd's. So sqrt naturally leads to less overheads and more safe concurrent tasks for large memory servers, which have large (thresh-freerun) gaps. peter: keep the per-CPU ratelimit for safeguarding the 1k+ tasks case CC: Peter Zijlstra <a.p.zijlstra@chello.nl> Reviewed-by: Andrea Righi <andrea@betterlinux.com> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
-
There are some imperfections in balanced_dirty_ratelimit. 1) large fluctuations The dirty_rate used for computing balanced_dirty_ratelimit is merely averaged in the past 200ms (very small comparing to the 3s estimation period for write_bw), which makes rather dispersed distribution of balanced_dirty_ratelimit. It's pretty hard to average out the singular points by increasing the estimation period. Considering that the averaging technique will introduce very undesirable time lags, I give it up totally. (btw, the 3s write_bw averaging time lag is much more acceptable because its impact is one-way and therefore won't lead to oscillations.) The more practical way is filtering -- most singular balanced_dirty_ratelimit points can be filtered out by remembering some prev_balanced_rate and prev_prev_balanced_rate. However the more reliable way is to guard balanced_dirty_ratelimit with task_ratelimit. 2) due to truncates and fs redirties, the (write_bw <=> dirty_rate) match could become unbalanced, which may lead to large systematical errors in balanced_dirty_ratelimit. The truncates, due to its possibly bumpy nature, can hardly be compensated smoothly. So let's face it. When some over-estimated balanced_dirty_ratelimit brings dirty_ratelimit high, dirty pages will go higher than the setpoint. task_ratelimit will in turn become lower than dirty_ratelimit. So if we consider both balanced_dirty_ratelimit and task_ratelimit and update dirty_ratelimit only when they are on the same side of dirty_ratelimit, the systematical errors in balanced_dirty_ratelimit won't be able to bring dirty_ratelimit far away. The balanced_dirty_ratelimit estimation may also be inaccurate near @limit or @freerun, however is less an issue. 3) since we ultimately want to - keep the fluctuations of task ratelimit as small as possible - keep the dirty pages around the setpoint as long time as possible the update policy used for (2) also serves the above goals nicely: if for some reason the dirty pages are high (task_ratelimit < dirty_ratelimit), and dirty_ratelimit is low (dirty_ratelimit < balanced_dirty_ratelimit), there is no point to bring up dirty_ratelimit in a hurry only to hurt both the above two goals. So, we make use of task_ratelimit to limit the update of dirty_ratelimit in two ways: 1) avoid changing dirty rate when it's against the position control target (the adjusted rate will slow down the progress of dirty pages going back to setpoint). 2) limit the step size. task_ratelimit is changing values step by step, leaving a consistent trace comparing to the randomly jumping balanced_dirty_ratelimit. task_ratelimit also has the nice smaller errors in stable state and typically larger errors when there are big errors in rate. So it's a pretty good limiting factor for the step size of dirty_ratelimit. Note that bdi->dirty_ratelimit is always tracking balanced_dirty_ratelimit. task_ratelimit is merely used as a limiting factor. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
-
It's all about bdi->dirty_ratelimit, which aims to be (write_bw / N) when there are N dd tasks. On write() syscall, use bdi->dirty_ratelimit ============================================ balance_dirty_pages(pages_dirtied) { task_ratelimit = bdi->dirty_ratelimit * bdi_position_ratio(); pause = pages_dirtied / task_ratelimit; sleep(pause); } On every 200ms, update bdi->dirty_ratelimit =========================================== bdi_update_dirty_ratelimit() { task_ratelimit = bdi->dirty_ratelimit * bdi_position_ratio(); balanced_dirty_ratelimit = task_ratelimit * write_bw / dirty_rate; bdi->dirty_ratelimit = balanced_dirty_ratelimit } Estimation of balanced bdi->dirty_ratelimit =========================================== balanced task_ratelimit ----------------------- balance_dirty_pages() needs to throttle tasks dirtying pages such that the total amount of dirty pages stays below the specified dirty limit in order to avoid memory deadlocks. Furthermore we desire fairness in that tasks get throttled proportionally to the amount of pages they dirty. IOW we want to throttle tasks such that we match the dirty rate to the writeout bandwidth, this yields a stable amount of dirty pages: dirty_rate == write_bw (1) The fairness requirement gives us: task_ratelimit = balanced_dirty_ratelimit == write_bw / N (2) where N is the number of dd tasks. We don't know N beforehand, but still can estimate balanced_dirty_ratelimit within 200ms. Start by throttling each dd task at rate task_ratelimit = task_ratelimit_0 (3) (any non-zero initial value is OK) After 200ms, we measured dirty_rate = # of pages dirtied by all dd's / 200ms write_bw = # of pages written to the disk / 200ms For the aggressive dd dirtiers, the equality holds dirty_rate == N * task_rate == N * task_ratelimit_0 (4) Or task_ratelimit_0 == dirty_rate / N (5) Now we conclude that the balanced task ratelimit can be estimated by write_bw balanced_dirty_ratelimit = task_ratelimit_0 * ---------- (6) dirty_rate Because with (4) and (5) we can get the desired equality (1): write_bw balanced_dirty_ratelimit == (dirty_rate / N) * ---------- dirty_rate == write_bw / N Then using the balanced task ratelimit we can compute task pause times like: task_pause = task->nr_dirtied / task_ratelimit task_ratelimit with position control ------------------------------------ However, while the above gives us means of matching the dirty rate to the writeout bandwidth, it at best provides us with a stable dirty page count (assuming a static system). In order to control the dirty page count such that it is high enough to provide performance, but does not exceed the specified limit we need another control. The dirty position control works by extending (2) to task_ratelimit = balanced_dirty_ratelimit * pos_ratio (7) where pos_ratio is a negative feedback function that subjects to 1) f(setpoint) = 1.0 2) df/dx < 0 That is, if the dirty pages are ABOVE the setpoint, we throttle each task a bit more HEAVY than balanced_dirty_ratelimit, so that the dirty pages are created less fast than they are cleaned, thus DROP to the setpoints (and the reverse). Based on (7) and the assumption that both dirty_ratelimit and pos_ratio remains CONSTANT for the past 200ms, we get task_ratelimit_0 = balanced_dirty_ratelimit * pos_ratio (8) Putting (8) into (6), we get the formula used in bdi_update_dirty_ratelimit(): write_bw balanced_dirty_ratelimit *= pos_ratio * ---------- (9) dirty_rate Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> -
No behavior change. Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
-
bdi_position_ratio() provides a scale factor to bdi->dirty_ratelimit, so that the resulted task rate limit can drive the dirty pages back to the global/bdi setpoints. Old scheme is, | free run area | throttle area ----------------------------------------+----------------------------> thresh^ dirty pages New scheme is, ^ task rate limit | | * | * | * |[free run] * [smooth throttled] | * | * | * ..bdi->dirty_ratelimit..........* | . * | . * | . * | . * | . * +-------------------------------.-----------------------*------------> setpoint^ limit^ dirty pages The slope of the bdi control line should be 1) large enough to pull the dirty pages to setpoint reasonably fast 2) small enough to avoid big fluctuations in the resulted pos_ratio and hence task ratelimit Since the fluctuation range of the bdi dirty pages is typically observed to be within 1-second worth of data, the bdi control line's slope is selected to be a linear function of bdi write bandwidth, so that it can adapt to slow/fast storage devices well. Assume the bdi control line pos_ratio = 1.0 + k * (dirty - bdi_setpoint) where k is the negative slope. If targeting for 12.5% fluctuation range in pos_ratio when dirty pages are fluctuating in range [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2], we get slope k = - 1 / (8 * write_bw) Let pos_ratio(x_intercept) = 0, we get the parameter used in code: x_intercept = bdi_setpoint + 8 * write_bw The global/bdi slopes are nicely complementing each other when the system has only one major bdi (indicated by bdi_thresh ~= thresh): 1) slope of global control line => scaling to the control scope size 2) slope of main bdi control line => scaling to the writeout bandwidth so that - in memory tight systems, (1) becomes strong enough to squeeze dirty pages inside the control scope - in large memory systems where the "gravity" of (1) for pulling the dirty pages to setpoint is too weak, (2) can back (1) up and drive dirty pages to bdi_setpoint ~= setpoint reasonably fast. Unfortunately in JBOD setups, the fluctuation range of bdi threshold is related to memory size due to the interferences between disks. In this case, the bdi slope will be weighted sum of write_bw and bdi_thresh. Given equations span = x_intercept - bdi_setpoint k = df/dx = - 1 / span and the extremum values span = bdi_thresh dx = bdi_thresh we get df = - dx / span = - 1.0 That means, when bdi_dirty deviates bdi_thresh up, pos_ratio and hence task ratelimit will fluctuate by -100%. peter: use 3rd order polynomial for the global control line CC: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Jan Kara <jack@suse.cz> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com> -
Introduce the BDI_DIRTIED counter. It will be used for estimating the bdi's dirty bandwidth. CC: Jan Kara <jack@suse.cz> CC: Michael Rubin <mrubin@google.com> CC: Peter Zijlstra <a.p.zijlstra@chello.nl> Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
-
* 'for-linus' of git://git.infradead.org/users/sameo/mfd-2.6: mfd: Fix generic irq chip ack function name for jz4740-adc
-
* 'for-linus' of git://github.com/tiwai/sound: ALSA: hda - Fix a regression of the position-buffer check
Commits on Oct 2, 2011
-
…-2.6-tip * 'perf-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip: perf tools: Fix raw sample reading
Commits on Oct 1, 2011
-
…hed-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip * 'irq-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip: irq: Fix check for already initialized irq_domain in irq_domain_add irq: Add declaration of irq_domain_simple_ops to irqdomain.h * 'x86-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip: x86/rtc: Don't recursively acquire rtc_lock * 'sched-urgent-for-linus' of git://tesla.tglx.de/git/linux-2.6-tip: posix-cpu-timers: Cure SMP wobbles sched: Fix up wchan borkage sched/rt: Migrate equal priority tasks to available CPUs
Commits on Sep 30, 2011
-
…urgent
-
David reported: Attached below is a watered-down version of rt/tst-cpuclock2.c from GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or similar. Run it several times, and you will see cases where the main thread will measure a process clock difference before and after the nanosleep which is smaller than the cpu-burner thread's individual thread clock difference. This doesn't make any sense since the cpu-burner thread is part of the top-level process's thread group. I've reproduced this on both x86-64 and sparc64 (using both 32-bit and 64-bit binaries). For example: [davem@boricha build-x86_64-linux]$ ./test process: before(0.001221967) after(0.498624371) diff(497402404) thread: before(0.000081692) after(0.498316431) diff(498234739) self: before(0.001223521) after(0.001240219) diff(16698) [davem@boricha build-x86_64-linux]$ The diff of 'process' should always be >= the diff of 'thread'. I make sure to wrap the 'thread' clock measurements the most tightly around the nanosleep() call, and that the 'process' clock measurements are the outer-most ones. --- #include <unistd.h> #include <stdio.h> #include <stdlib.h> #include <time.h> #include <fcntl.h> #include <string.h> #include <errno.h> #include <pthread.h> static pthread_barrier_t barrier; static void *chew_cpu(void *arg) { pthread_barrier_wait(&barrier); while (1) __asm__ __volatile__("" : : : "memory"); return NULL; } int main(void) { clockid_t process_clock, my_thread_clock, th_clock; struct timespec process_before, process_after; struct timespec me_before, me_after; struct timespec th_before, th_after; struct timespec sleeptime; unsigned long diff; pthread_t th; int err; err = clock_getcpuclockid(0, &process_clock); if (err) return 1; err = pthread_getcpuclockid(pthread_self(), &my_thread_clock); if (err) return 1; pthread_barrier_init(&barrier, NULL, 2); err = pthread_create(&th, NULL, chew_cpu, NULL); if (err) return 1; err = pthread_getcpuclockid(th, &th_clock); if (err) return 1; pthread_barrier_wait(&barrier); err = clock_gettime(process_clock, &process_before); if (err) return 1; err = clock_gettime(my_thread_clock, &me_before); if (err) return 1; err = clock_gettime(th_clock, &th_before); if (err) return 1; sleeptime.tv_sec = 0; sleeptime.tv_nsec = 500000000; nanosleep(&sleeptime, NULL); err = clock_gettime(th_clock, &th_after); if (err) return 1; err = clock_gettime(my_thread_clock, &me_after); if (err) return 1; err = clock_gettime(process_clock, &process_after); if (err) return 1; diff = process_after.tv_nsec - process_before.tv_nsec; printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", process_before.tv_sec, process_before.tv_nsec, process_after.tv_sec, process_after.tv_nsec, diff); diff = th_after.tv_nsec - th_before.tv_nsec; printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", th_before.tv_sec, th_before.tv_nsec, th_after.tv_sec, th_after.tv_nsec, diff); diff = me_after.tv_nsec - me_before.tv_nsec; printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n", me_before.tv_sec, me_before.tv_nsec, me_after.tv_sec, me_after.tv_nsec, diff); return 0; } This is due to us using p->se.sum_exec_runtime in thread_group_cputime() where we iterate the thread group and sum all data. This does not take time since the last schedule operation (tick or otherwise) into account. We can cure this by using task_sched_runtime() at the cost of having to take locks. This also means we can (and must) do away with thread_group_sched_runtime() since the modified thread_group_cputime() is now more accurate and would deadlock when called from thread_group_sched_runtime(). Aside of that it makes the function safe on 32 bit systems. The old code added t->se.sum_exec_runtime unprotected. sum_exec_runtime is a 64bit value and could be changed on another cpu at the same time. Reported-by: David Miller <davem@davemloft.net> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins Tested-by: David Miller <davem@davemloft.net> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> -
The commit a810364 ALSA: hda - Handle -1 as invalid position, too caused a regression on some machines that require the position-buffer instead of LPIB, e.g. resulting in noises with mic recording with PulseAudio. This patch fixes the detection by delaying the test at the timing as same as 3.0, i.e. doing the position check only when requested in azx_position_ok(). Reported-and-tested-by: Rocko Requin <rockorequin@hotmail.com> Signed-off-by: Takashi Iwai <tiwai@suse.de>
-
__find_resource() incorrectly returns a resource window which overlaps an existing allocated window. This happens when the parent's resource-window spans 0x00000000 to 0xffffffff and is entirely allocated to all its children resource-windows. __find_resource() looks for gaps in resource allocation among the children resource windows. When it encounters the last child window it blindly tries the range next to one allocated to the last child. Since the last child's window ends at 0xffffffff the calculation overflows, leading the algorithm to believe that any window in the range 0x0000000 to 0xfffffff is available for allocation. This leads to a conflicting window allocation. Michal Ludvig reported this issue seen on his platform. The following patch fixes the problem and has been verified by Michal. I believe this bug has been there for ages. It got exposed by git commit 2bbc694 ("PCI : ability to relocate assigned pci-resources") Signed-off-by: Ram Pai <linuxram@us.ibm.com> Tested-by: Michal Ludvig <mludvig@logix.net.nz> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-
* 'for-linus' of git://github.com/NewDreamNetwork/ceph-client: libceph: fix pg_temp mapping update libceph: fix pg_temp mapping calculation libceph: fix linger request requeuing libceph: fix parse options memory leak libceph: initialize ack_stamp to avoid unnecessary connection reset
-
* 'v4l_for_linus' of git://linuxtv.org/mchehab/for_linus: [media] omap3isp: Fix build error in ispccdc.c [media] uvcvideo: Fix crash when linking entities [media] v4l: Make sure we hold a reference to the v4l2_device before using it [media] v4l: Fix use-after-free case in v4l2_device_release [media] uvcvideo: Set alternate setting 0 on resume if the bus has been reset [media] OMAP_VOUT: Fix build break caused by update_mode removal in DSS2
-
* 'for-linus' of git://git390.marist.edu/pub/scm/linux-2.6: [S390] cio: fix cio_tpi ignoring adapter interrupts [S390] gmap: always up mmap_sem properly [S390] Do not clobber personality flags on exec
-
* git://github.com/davem330/sparc: sparc64: Force the execute bit in OpenFirmware's translation entries. sparc: Make '-p' boot option meaningful again. sparc, exec: remove redundant addr_limit assignment sparc64: Future proof Niagara cpu detection.
-
…p/linux * 'drm-intel-fixes' of git://people.freedesktop.org/~keithp/linux: drm/i915: FBC off for ironlake and older, otherwise on by default drm/i915: Enable SDVO hotplug interrupts for HDMI and DVI drm/i915: Enable dither whenever display bpc < frame buffer bpc
-
Apple Quad G5 has some oddity in it's device-tree which causes the new generic matching code to fail to relate nodes for PCI-E devices below U4 with their respective struct pci_dev. This breaks graphics on those machines among others. This fixes it using a quirk which copies the node pointer from the host bridge for the root complex, which makes the generic code work for the children afterward. Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-
Commit d5767c5 ("bootup: move 'usermodehelper_enable()' to the end of do_basic_setup()") moved 'usermodehelper_enable()' to end of do_basic_setup() to after the initcalls. But then I get failed to let uvesafb work on my computer, and lose the splash boot. So maybe we could start usermodehelper_enable a little early to make some task work that need eary init with the help of user mode. [ I would *really* prefer that initcalls not call into user space - even the real 'init' hasn't been execve'd yet, after all! But for uvesafb it really does look like we don't have much choice. I considered doing this when we mount the root filesystem, but depending on config options that is in multiple places. We could do the usermode helper enable as a rootfs_initcall().. So I'm just using wang yanqing's trivial patch. It's not wonderful, but it's simple and should work. We should revisit this some day, though. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commits on Sep 29, 2011
-
Wrong pointer is being passed for raw data sanity checking, when parsing sample event. This ends up with invalid event and perf record being stuck in __perf_session__process_events function during processing build IDs (process_buildids function). Following command hangs up in my setup: ./perf record -e raw_syscalls:sys_enter ls The fix is to use proper pointer to the raw data instead of the 'u' union. Reviewed-by: David Ahern <dsahern@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Eric Dumazet <eric.dumazet@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Neil Horman <nhorman@tuxdriver.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1317308709-9474-2-git-send-email-jolsa@redhat.com Signed-off-by: Jiri Olsa <jolsa@redhat.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-
In the OF 'translations' property, the template TTEs in the mappings never specify the executable bit. This is the case even though some of these mappings are for OF's code segment. Therefore, we need to force the execute bit on in every mapping. This problem can only really trigger on Niagara/sun4v machines and the history behind this is a little complicated. Previous to sun4v, the sun4u TTE entries lacked a hardware execute permission bit. So OF didn't have to ever worry about setting anything to handle executable pages. Any valid TTE loaded into the I-TLB would be respected by the chip. But sun4v Niagara chips have a real hardware enforced executable bit in their TTEs. So it has to be set or else the I-TLB throws an instruction access exception with type code 6 (protection violation). We've been extremely fortunate to not get bitten by this in the past. The best I can tell is that the OF's mappings for it's executable code were mapped using permanent locked mappings on sun4v in the past. Therefore, the fact that we didn't have the exec bit set in the OF translations we would use did not matter in practice. Thanks to Greg Onufer for helping me track this down. Signed-off-by: David S. Miller <davem@davemloft.net>
Commits on Sep 28, 2011
-
Doing it just before starting to call into cpu_idle() made a sick kind of sense only because the original bug we fixed (see commit 288d5ab: "Boot up with usermodehelper disabled") was about problems with some scheduler data structures not being initialized, and they had better be initialized at that point. But it really didn't make any other conceptual sense, and doing it after the initial "schedule()" call for the idle thread actually opened up a race: what if the main initialization thread did everything without needing to sleep, and got all the way into user land too? Without actually having scheduled back to the idle thread? Now, in normal circumstances that doesn't ever happen, but it looks like Richard Cochran triggered exactly that on his ARM IXP4xx machines: "I have some ARM IXP4xx based machines that use the two on chip MAC ports (aka NPEs). The NPE needs a firmware in order to function. Ever since the following commit [that 288d5ab one], it is no longer possible to bring up the interfaces during the init scripts." with a call trace showing an ioctl coming from user space. Richard says: "The init is busybox, and the startup script does mount, syslogd, and then ifup, so that all can go by quickly." The fix is to move the usermodehelper_enable() into the main 'init' thread, and just put it after we've done all our initcalls. By then, everything really should be up, but we've obviously not actually started the user-mode portion of init yet. Reported-and-tested-by: Richard Cochran <richardcochran@gmail.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-
The incremental map updates have a record for each pg_temp mapping that is to be add/updated (len > 0) or removed (len == 0). The old code was written as if the updates were a complete enumeration; that was just wrong. Update the code to remove 0-length entries and drop the rbtree traversal. This avoids misdirected (and hung) requests that manifest as server errors like [WRN] client4104 10.0.1.219:0/275025290 misdirected client4104.1:129 0.1 to osd0 not [1,0] in e11/11 Signed-off-by: Sage Weil <sage@newdream.net>
-
We need to apply the modulo pg_num calculation before looking up a pgid in the pg_temp mapping rbtree. This fixes pg_temp mappings, and fixes (some) misdirected requests that result in messages like [WRN] client4104 10.0.1.219:0/275025290 misdirected client4104.1:129 0.1 to osd0 not [1,0] in e11/11 on the server and stall make the client block without getting a reply (at least until the pg_temp mapping goes way, but that can take a long long time). Reorder calc_pg_raw() a bit to make more sense. Signed-off-by: Sage Weil <sage@newdream.net>
-
* git://github.com/davem330/net: ipv6-multicast: Fix memory leak in IPv6 multicast. ipv6: check return value for dst_alloc net: check return value for dst_alloc ipv6-multicast: Fix memory leak in input path. bnx2x: add missing break in bnx2x_dcbnl_get_cap bnx2x: fix WOL by enablement PME in config space bnx2x: fix hw attention handling net: fix a typo in Documentation/networking/scaling.txt ath9k: Fix a dma warning/memory leak rtlwifi: rtl8192cu: Fix unitialized struct iwlagn: fix dangling scan request batman-adv: do_bcast has to be true for broadcast packets only cfg80211: Fix validation of AKM suites iwlegacy: do not use interruptible waits iwlegacy: fix command queue timeout ath9k_hw: Fix Rx DMA stuck for AR9003 chips
-
* git://bedivere.hansenpartnership.com/git/scsi-rc-fixes-2.6: [SCSI] 3w-9xxx: fix iommu_iova leak [SCSI] cxgb3i: convert cdev->l2opt to use rcu to prevent NULL dereference [SCSI] scsi: qla4xxx needs libiscsi.o [SCSI] libsas: fix failure to revalidate domain for anything but the first expander child. [SCSI] aacraid: reset should disable MSI interrupt
-
* 'for-linus' of git://git.kernel.dk/linux-block: block: Free queue resources at blk_release_queue()
NewerOlder