1
0
mirror of https://github.com/Zygo/bees.git synced 2025-05-17 21:35:45 +02:00

FdCache: clear cache on every new transid / crawl cycle

The periodic cache age check was not protected by a lock, so multiple
threads may decide to concurrently clear the cache.  This led to
duplicate log messages.

Fix by moving the cache expiry trigger out of FdCache and into Roots,
which knows when transids change and can perform cache clears at exactly
the time they are most relevant, i.e. after something that was deleted
becomes permanently so.

This removes the last references to BEES_COMMIT_INTERVAL, so get rid
of its definition too.

Signed-off-by: Zygo Blaxell <bees@furryterror.org>
This commit is contained in:
Zygo Blaxell 2018-01-24 23:32:33 -05:00
parent 72857e84c0
commit ded26ff044
3 changed files with 26 additions and 21 deletions

View File

@ -40,30 +40,26 @@ BeesFdCache::BeesFdCache()
m_file_cache.max_size(BEES_FILE_FD_CACHE_SIZE);
}
void
BeesFdCache::clear()
{
BEESNOTE("Clearing root FD cache to enable subvol delete");
m_root_cache.clear();
BEESCOUNT(root_clear);
BEESNOTE("Clearing open FD cache to enable file delete");
m_file_cache.clear();
BEESCOUNT(open_clear);
}
Fd
BeesFdCache::open_root(shared_ptr<BeesContext> ctx, uint64_t root)
{
// Don't hold root FDs open too long.
// The open FDs prevent snapshots from being deleted.
// cleaner_kthread just keeps skipping over the open dir and all its children.
if (m_root_cache_timer.age() > BEES_COMMIT_INTERVAL) {
BEESLOGINFO("Clearing root FD cache to enable subvol delete");
m_root_cache.clear();
m_root_cache_timer.reset();
BEESCOUNT(root_clear);
}
return m_root_cache(ctx, root);
}
Fd
BeesFdCache::open_root_ino(shared_ptr<BeesContext> ctx, uint64_t root, uint64_t ino)
{
if (m_file_cache_timer.age() > BEES_COMMIT_INTERVAL) {
BEESLOGINFO("Clearing open FD cache to enable file delete");
m_file_cache.clear();
m_file_cache_timer.reset();
BEESCOUNT(open_clear);
}
return m_file_cache(ctx, root, ino);
}

View File

@ -335,11 +335,22 @@ BeesRoots::crawl_thread()
// Monitor transid_max and wake up roots when it changes
BEESNOTE("tracking transids");
auto last_count = m_transid_re.count();
while (true) {
// Make sure we have a full complement of crawlers
// Calls transid_max() which updates m_transid_re
insert_new_crawl();
// Don't hold root FDs open too long.
// The open FDs prevent snapshots from being deleted.
// cleaner_kthread just keeps skipping over the open dir and all its children.
// Even open files are a problem if they're big enough.
auto new_count = m_transid_re.count();
if (new_count != last_count) {
m_ctx->fd_cache()->clear();
}
last_count = new_count;
BEESNOTE("waiting for next transid " << m_transid_re);
// We don't use wait_for here because somebody needs to
// be updating m_transid_re from time to time.

View File

@ -59,11 +59,8 @@ const off_t BLOCK_SIZE_HASHTAB_EXTENT = 16 * 1024 * 1024;
// Bytes per second we want to flush (8GB every two hours)
const double BEES_FLUSH_RATE = 8.0 * 1024 * 1024 * 1024 / 7200.0;
// How long we should wait for new btrfs transactions
const double BEES_COMMIT_INTERVAL = 900;
// Interval between writing non-hash-table things to disk, and starting new subvol crawlers
const int BEES_WRITEBACK_INTERVAL = BEES_COMMIT_INTERVAL;
// Interval between writing crawl state to disk
const int BEES_WRITEBACK_INTERVAL = 900;
// Statistics reports while scanning
const int BEES_STATS_INTERVAL = 3600;
@ -92,7 +89,7 @@ const double BEES_TOO_LONG = 5.0;
// Avoid any extent where LOGICAL_INO takes this long
// const double BEES_TOXIC_DURATION = 9.9;
// EXPERIMENT: Kernel v4.14+ may let us ignore toxicity
const double BEES_TOXIC_DURATION = BEES_COMMIT_INTERVAL;
const double BEES_TOXIC_DURATION = 99.9;
// How long between hash table histograms
const double BEES_HASH_TABLE_ANALYZE_INTERVAL = BEES_STATS_INTERVAL;
@ -657,6 +654,7 @@ public:
Fd open_root(shared_ptr<BeesContext> ctx, uint64_t root);
Fd open_root_ino(shared_ptr<BeesContext> ctx, uint64_t root, uint64_t ino);
void insert_root_ino(shared_ptr<BeesContext> ctx, Fd fd);
void clear();
};
struct BeesResolveAddrResult {