From 5e64aa222b106ef3bd091346ebba807e10dc449e Mon Sep 17 00:00:00 2001 From: Zdenek Kabelac Date: Fri, 2 Oct 2020 17:42:50 +0200 Subject: [PATCH] bcache: fix busy loop with too many errors When bcache tries to write data to a faulty device, it may get out of caching blocks and then just busy-loops on a CPU - so this check protects this by checking if there is already max_io (~64) errored blocks. --- WHATS_NEW | 1 + lib/device/bcache.c | 5 +++++ 2 files changed, 6 insertions(+) diff --git a/WHATS_NEW b/WHATS_NEW index 7dae2ec5e..2cfb79ba0 100644 --- a/WHATS_NEW +++ b/WHATS_NEW @@ -1,5 +1,6 @@ Version 2.02.188 - ================================== + Fix bcache when device has too many failing writes. Fix bcache waiting for IO completion with failing disks. Configure use own python path name order to prefer using python3. Enhance reporting and error handling when creating thin volumes. diff --git a/lib/device/bcache.c b/lib/device/bcache.c index 9d4ef90a9..e173129fe 100644 --- a/lib/device/bcache.c +++ b/lib/device/bcache.c @@ -957,6 +957,11 @@ static struct block *_new_block(struct bcache *cache, int fd, block_address i, b if (dm_list_empty(&cache->io_pending)) _writeback(cache, 16); // FIXME: magic number _wait_all(cache); + if (dm_list_size(&cache->errored) >= cache->max_io) { + log_debug("bcache no new blocks for di %d index %u with >%d errors.", + fd, (uint32_t) i, cache->max_io); + return NULL; + } } else { log_error("bcache no new blocks for fd %d index %u", fd, (uint32_t) i);