netdata - Mirror of https://github.com/netdata/netdata

diff options

author	Costa Tsaousis <costa@netdata.cloud>	2023-01-30 20:36:16 +0200
committer	GitHub <noreply@github.com>	2023-01-30 20:36:16 +0200
commit	7f8f11eb373dfc7bf6ac5a03e57a1b03487a279e (patch)
tree	a79f74e904690145b2c6807ca512eec1dd2160ed /.github
parent	fd7f39a74426d16f01559bd5aac1a6f90baef57f (diff)

DBENGINE v2 - improvements part 11 (#14337)

* acquiring / releasing interface for metrics * metrics registry statistics * cleanup metrics registry by deleting metrics when they dont have retention anymore; do not double copy the data of pages to be flushed * print the tier in retention summary * Open files with buffered instead of direct I/O (test) * added more metrics stats and fixed unittest * rename writer functions to avoid confusion with refcounting * do not release a metric that is not acquired * Revert to use direct I/O on write -- use direct I/O on read as well * keep track of ARAL overhead and add it to the memory chart * aral full check via api * Cleanup * give names to ARALs and PGCs * aral improvements * restore query expansion to the future * prefer higher resolution tier when switching plans * added extent read statistics * smoother joining of tiers at query engine * fine tune aral max allocation size * aral restructuring to hide its internals from the rest of netdata * aral restructuring; addtion of defrag option to aral to keep the linked list sorted - enabled by default to test it * fully async aral * some statistics and cleanup * fix infinite loop while calculating retention * aral docs and defragmenting disabled by default * fix bug and add optimization when defragmenter is not enabled * aral stress test * aral speed report and documentation * added internal checks that all pages are full * improve internal log about metrics deletion * metrics registry uses one aral per partition * metrics registry aral max size to 512 elements per page * remove data_structures/README.md dependency --------- Co-authored-by: Stelios Fragkakis <52996999+stelfrag@users.noreply.github.com>

Diffstat (limited to '.github')

0 files changed, 0 insertions, 0 deletions

/* * * Copyright (c) 2009, Microsoft Corporation. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, * version 2, as published by the Free Software Foundation. * * This program is distributed in the hope it will be useful, but WITHOUT * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for * more details. * * You should have received a copy of the GNU General Public License along with * this program; if not, write to the Free Software Foundation, Inc., 59 Temple * Place - Suite 330, Boston, MA 02111-1307 USA. * * Authors: * Haiyang Zhang <haiyangz@microsoft.com> * Hank Janssen <hjanssen@microsoft.com> * K. Y. Srinivasan <kys@microsoft.com> * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/mm.h> #include <linux/hyperv.h> #include <linux/uio.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include "hyperv_vmbus.h" #define VMBUS_PKT_TRAILER 8 /* * When we write to the ring buffer, check if the host needs to * be signaled. Here is the details of this protocol: * * 1. The host guarantees that while it is draining the * ring buffer, it will set the interrupt_mask to * indicate it does not need to be interrupted when * new data is placed. * * 2. The host guarantees that it will completely drain * the ring buffer before exiting the read loop. Further, * once the ring buffer is empty, it will clear the * interrupt_mask and re-check to see if new data has * arrived. * * KYS: Oct. 30, 2016: * It looks like Windows hosts have logic to deal with DOS attacks that * can be triggered if it receives interrupts when it is not expecting * the interrupt. The host expects interrupts only when the ring * transitions from empty to non-empty (or full to non full on the guest * to host ring). * So, base the signaling decision solely on the ring state until the * host logic is fixed. */ static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel) { struct hv_ring_buffer_info *rbi = &channel->outbound; virt_mb(); if (READ_ONCE(rbi->ring_buffer->interrupt_mask)) return; /* check interrupt_mask before read_index */ virt_rmb(); /* * This is the only case we need to signal when the * ring transitions from being empty to non-empty. */ if (old_write == READ_ONCE(rbi->ring_buffer->read_index)) vmbus_setevent(channel); } /* Get the next write location for the specified ring buffer. */ static inline u32 hv_get_next_write_location(struct hv_ring_buffer_info *ring_info) { u32 next = ring_info->ring_buffer->write_index; return next; } /* Set the next write location for the specified ring buffer. */ static inline void hv_set_next_write_location(struct hv_ring_buffer_info *ring_info, u32 next_write_location) { ring_info->ring_buffer->write_index = next_write_location; } /* Get the next read location for the specified ring buffer. */ static inline u32 hv_get_next_read_location(const struct hv_ring_buffer_info *ring_info) { return ring_info->ring_buffer->read_index; } /* * Get the next read location + offset for the specified ring buffer. * This allows the caller to skip. */ static inline u32 hv_get_next_readlocation_withoffset(const struct hv_ring_buffer_info *ring_info, u32 offset) { u32 next = ring_info->ring_buffer->read_index; next += offset; if (next >= ring_info->ring_datasize) next -= ring_info->ring_datasize; return next; } /* Set the next read location for the specified ring buffer. */ static inline void hv_set_next_read_location(struct hv_ring_buffer_info *ring_info, u32 next_read_location) { ring_info->ring_buffer->read_index = next_read_location; ring_info->priv_read_index = next_read_location; } /* Get the size of the ring buffer. */ static inline u32 hv_get_ring_buffersize(const struct hv_ring_buffer_info *ring_info) { return ring_info->ring_datasize; } /* Get the read and write indices as u64 of the specified ring buffer. */ static inline u64 hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info) { return (u64)ring_info->ring_buffer->write_index << 32; } /* * Helper routine to copy to source from ring buffer. * Assume there is enough room. Handles wrap-around in src case only!! */ static u32 hv_copyfrom_ringbuffer( const struct hv_ring_buffer_info *ring_info, void *dest, u32 destlen, u32 start_read_offset) { void *ring_buffer = hv_get_ring_buffer(ring_info); u32 ring_buffer_size = hv_get_ring_buffersize(ring_info); memcpy(dest, ring_buffer + start_read_offset, destlen); start_read_offset += destlen; if (start_read_offset >= ring_buffer_size) start_read_offset -= ring_buffer_size; return start_read_offset; } /* * Helper routine to copy from source to ring buffer. * Assume there is enough room. Handles wrap-around in dest case only!! */ static u32 hv_copyto_ringbuffer( struct hv_ring_buffer_info *ring_info, u32 start_write_offset, const void *src, u32 srclen) { void *ring_buffer = hv_get_ring_buffer(ring_info); u32 ring_buffer_size = hv_get_ring_buffersize(ring_info); memcpy(ring_buffer + start_write_offset, src, srclen); start_write_offset += srclen; if (start_write_offset >= ring_buffer_size) start_write_offset -= ring_buffer_size; return start_write_offset; } /* Get various debug metrics for the specified ring buffer. */ void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info, struct hv_ring_buffer_debug_info *debug_info) { u32 bytes_avail_towrite; u32 bytes_avail_toread; if (ring_info->ring_buffer) { hv_get_ringbuffer_availbytes(ring_info, &bytes_avail_toread, &bytes_avail_towrite); debug_info->bytes_avail_toread = bytes_avail_toread; debug_info->bytes_avail_towrite = bytes_avail_towrite; debug_info->current_read_index = ring_info->ring_buffer->read_index; debug_info->current_write_index = ring_info->ring_buffer->write_index; debug_info->current_interrupt_mask = ring_info->ring_buffer->interrupt_mask; } } EXPORT_SYMBOL_GPL(hv_ringbuffer_get_debuginfo); /* Initialize the ring buffer. */ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info, struct page *pages, u32 page_cnt) { int i; struct page **pages_wraparound; BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE)); memset(ring_info, 0, sizeof(struct hv_ring_buffer_info)); /* * First page holds struct hv_ring_buffer, do wraparound mapping for * the rest. */ pages_wraparound = kzalloc(sizeof(struct page *) * (page_cnt * 2 - 1), GFP_KERNEL); if (!pages_wraparound) return -ENOMEM; pages_wraparound[0] = pages; for (i = 0; i < 2 * (page_cnt - 1); i++) pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1]; ring_info->ring_buffer = (struct hv_ring_buffer *) vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL); kfree(pages_wraparound); if (!ring_info->ring_buffer) return -ENOMEM; ring_info->ring_buffer->read_index = ring_info->ring_buffer->write_index = 0; /* Set the feature bit for enabling flow control. */ ring_info->ring_buffer->feature_bits.value = 1; ring_info->ring_size = page_cnt << PAGE_SHIFT; ring_info->ring_datasize = ring_info->ring_size - sizeof(struct hv_ring_buffer); spin_lock_init(&ring_info->ring_lock); return 0; } /* Cleanup the ring buffer. */ void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info) { vunmap(ring_info->ring_buffer); } /* Write to the ring buffer. */ int hv_ringbuffer_write(struct vmbus_channel *channel, const struct kvec *kv_list, u32 kv_count) { int i; u32 bytes_avail_towrite; u32 totalbytes_towrite = sizeof(u64); u32 next_write_location; u32 old_write; u64 prev_indices; unsigned long flags; struct hv_ring_buffer_info *outring_info = &channel->outbound; if (channel->rescind) return -ENODEV; for (i = 0; i < kv_count; i++) totalbytes_towrite += kv_list[i].iov_len; spin_lock_irqsave(&outring_info->ring_lock, flags); bytes_avail_towrite = hv_get_bytes_to_write(outring_info); /* * If there is only room for the packet, assume it is full. * Otherwise, the next time around, we think the ring buffer * is empty since the read index == write index. */ if (bytes_avail_towrite <= totalbytes_towrite) { spin_unlock_irqrestore(&outring_info->ring_lock, flags); return -EAGAIN; } /* Write to the ring buffer */ next_write_location = hv_get_next_write_location(outring_info); old_write = next_write_location; for (i = 0; i < kv_count; i++) { next_write_location = hv_copyto_ringbuffer(outring_info, next_write_location,


context:
space:
mode: