From f15d6a54575567c6d69b6f1ffc000d2df5a8f206 Mon Sep 17 00:00:00 2001 From: Alexander Motin Date: Mon, 11 Nov 2019 20:27:59 +0300 Subject: [PATCH] Improve logging of 128KB writes Before my ZIL space optimization few years ago 128KB writes were logged as two 64KB+ records in two 128KB log blocks. After that change it became ~127KB+/1KB+ in two 128KB log blocks to free space in the second block for another record. Unfortunately in case of 128KB only writes, when space in the second block remained unused, that change increased write latency by unbalancing checksum computation and write times between parallel threads. It also didn't help with SLOG space efficiency in that case. This change introduces new 68KB log block size, used for both writes below 67KB and 128KB-sharp writes. Writes of 68-127KB are still using one 128KB block to not increase processing overhead. Writes above 131KB are still using full 128KB blocks, since possible saving there is small. Mixed loads will likely also fall back to previous 128KB, since code uses maximum of the last 16 requested block sizes. Reviewed-by: Matt Ahrens Reviewed-by: Brian Behlendorf Signed-off-by: Alexander Motin Closes #9409 --- module/zfs/zil.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-) diff --git a/module/zfs/zil.c b/module/zfs/zil.c index 6ca0bc73e..1c122f35a 100644 --- a/module/zfs/zil.c +++ b/module/zfs/zil.c @@ -1414,11 +1414,17 @@ zil_lwb_write_open(zilog_t *zilog, lwb_t *lwb) * aligned to 4KB) actually gets written. However, we can't always just * allocate SPA_OLD_MAXBLOCKSIZE as the slog space could be exhausted. */ -uint64_t zil_block_buckets[] = { - 4096, /* non TX_WRITE */ - 8192+4096, /* data base */ - 32*1024 + 4096, /* NFS writes */ - UINT64_MAX +struct { + uint64_t limit; + uint64_t blksz; +} zil_block_buckets[] = { + { 4096, 4096 }, /* non TX_WRITE */ + { 8192 + 4096, 8192 + 4096 }, /* database */ + { 32768 + 4096, 32768 + 4096 }, /* NFS writes */ + { 65536 + 4096, 65536 + 4096 }, /* 64KB writes */ + { 131072, 131072 }, /* < 128KB writes */ + { 131072 +4096, 65536 + 4096 }, /* 128KB writes */ + { UINT64_MAX, SPA_OLD_MAXBLOCKSIZE}, /* > 128KB writes */ }; /* @@ -1502,9 +1508,9 @@ zil_lwb_write_issue(zilog_t *zilog, lwb_t *lwb) * pool log space. */ zil_blksz = zilog->zl_cur_used + sizeof (zil_chain_t); - for (i = 0; zil_blksz > zil_block_buckets[i]; i++) + for (i = 0; zil_blksz > zil_block_buckets[i].limit; i++) continue; - zil_blksz = MIN(zil_block_buckets[i], zilog->zl_max_block_size); + zil_blksz = MIN(zil_block_buckets[i].blksz, zilog->zl_max_block_size); zilog->zl_prev_blks[zilog->zl_prev_rotor] = zil_blksz; for (i = 0; i < ZIL_PREV_BLKS; i++) zil_blksz = MAX(zil_blksz, zilog->zl_prev_blks[i]);