[PATCH xfs v2 0/2] Separate xfs_log_vec/iovec to save memory

[PATCH xfs v2 0/2] Separate xfs_log_vec/iovec to save memory

[alexjlzheng]

From: Jinliang Zheng <alexjlzheng@tencent.com>

xfs_log_iovec dominates the memory usage of the
xfs_log_vec/xfs_log_iovec combination, and it is no longer useful after
the data is flushed to the iclog. This patchset separates xfs_log_iovec
from xfs_log_vec and releases them early to save memory.

Changelog:
V1:
- https://lore.kernel.org/linux-xfs/20240623123119.3562031-1-alexjlzheng@tencent.com/

V2:
- add kmem_cache for small object xfs_log_vec
- reduce redundant free and allocation of xfs_log_vec

Jinliang Zheng (2):
  xfs: add xfs_log_vec_cache for separate xfs_log_vec/xfs_log_iovec
  xfs: make xfs_log_iovec independent from xfs_log_vec and free it early

 fs/xfs/xfs_log.c     |  3 +++
 fs/xfs/xfs_log.h     | 10 ++++++++--
 fs/xfs/xfs_log_cil.c | 33 ++++++++++++++++++++-------------
 fs/xfs/xfs_super.c   |  9 +++++++++
 4 files changed, 40 insertions(+), 15 deletions(-)

-- 
2.39.3

[PATCH xfs v2 1/2] xfs: add xfs_log_vec_cache for separate xfs_log_vec/xfs_log_iovec

[alexjlzheng]

From: Jinliang Zheng <alexjlzheng@tencent.com>

Signed-off-by: Jinliang Zheng <alexjlzheng@tencent.com>
---
 fs/xfs/xfs_log.c   | 1 +
 fs/xfs/xfs_log.h   | 2 ++
 fs/xfs/xfs_super.c | 9 +++++++++
 3 files changed, 12 insertions(+)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 416c15494983..49e676061f2f 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -21,6 +21,7 @@
 #include "xfs_sb.h"
 #include "xfs_health.h"
 
+struct kmem_cache	*xfs_log_vec_cache;
 struct kmem_cache	*xfs_log_ticket_cache;
 
 /* Local miscellaneous function prototypes */
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index d69acf881153..9cc10acf7bcd 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -20,6 +20,8 @@ struct xfs_log_vec {
 	int			lv_size;	/* size of allocated lv */
 };
 
+extern struct kmem_cache *xfs_log_vec_cache;
+
 #define XFS_LOG_VEC_ORDERED	(-1)
 
 /*
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 27e9f749c4c7..7e94f9439a8f 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -2222,8 +2222,16 @@ xfs_init_caches(void)
 	if (!xfs_parent_args_cache)
 		goto out_destroy_xmi_cache;
 
+	xfs_log_vec_cache = kmem_cache_create("xfs_log_vec",
+						sizeof(struct xfs_log_vec),
+						0, 0, NULL);
+	if (!xfs_log_vec_cache)
+		goto out_destroy_args_cache;
+
 	return 0;
 
+ out_destroy_args_cache:
+	kmem_cache_destroy(xfs_parent_args_cache);
  out_destroy_xmi_cache:
 	kmem_cache_destroy(xfs_xmi_cache);
  out_destroy_xmd_cache:
@@ -2286,6 +2294,7 @@ xfs_destroy_caches(void)
 	 * destroy caches.
 	 */
 	rcu_barrier();
+	kmem_cache_destroy(xfs_log_vec_cache);
 	kmem_cache_destroy(xfs_parent_args_cache);
 	kmem_cache_destroy(xfs_xmd_cache);
 	kmem_cache_destroy(xfs_xmi_cache);
-- 
2.39.3

[PATCH xfs v2 2/2] xfs: make xfs_log_iovec independent from xfs_log_vec and free it early

[alexjlzheng]

From: Jinliang Zheng <alexjlzheng@tencent.com>

When the contents of the xfs_log_vec/xfs_log_iovec combination are
written to iclog, xfs_log_iovec loses its meaning in continuing to exist
in memory, because iclog already has a copy of its contents. We only
need to keep xfs_log_vec that takes up very little memory to find the
xfs_log_item that needs to be added to AIL after we flush the iclog into
the disk log space.

Because xfs_log_iovec dominates most of the memory usage of the
xfs_log_vec/xfs_log_iovec combination, retaining xfs_log_iovec until
iclog is flushed into the disk log space and releasing together with
xfs_log_vec is a significant waste of memory.

This patch separates the memory of xfs_log_iovec from that of
xfs_log_vec, and releases the memory of xfs_log_iovec in advance to save
memory.

Signed-off-by: Jinliang Zheng <alexjlzheng@tencent.com>
---
 fs/xfs/xfs_log.c     |  2 ++
 fs/xfs/xfs_log.h     |  8 ++++++--
 fs/xfs/xfs_log_cil.c | 33 ++++++++++++++++++++-------------
 3 files changed, 28 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 49e676061f2f..84a01ce61c96 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -2527,6 +2527,8 @@ xlog_write(
 			xlog_write_full(lv, ticket, iclog, &log_offset,
 					 &len, &record_cnt, &data_cnt);
 		}
+		if (lv->lv_flags & XFS_LOG_VEC_DYNAMIC)
+			kvfree(lv->lv_iovecp);
 	}
 	ASSERT(len == 0);
 
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 9cc10acf7bcd..035fda96bfcc 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -6,6 +6,8 @@
 #ifndef	__XFS_LOG_H__
 #define __XFS_LOG_H__
 
+#define XFS_LOG_VEC_DYNAMIC	(1 << 0)
+
 struct xfs_cil_ctx;
 
 struct xfs_log_vec {
@@ -17,7 +19,8 @@ struct xfs_log_vec {
 	char			*lv_buf;	/* formatted buffer */
 	int			lv_bytes;	/* accounted space in buffer */
 	int			lv_buf_len;	/* aligned size of buffer */
-	int			lv_size;	/* size of allocated lv */
+	int			lv_size;	/* size of allocated iovecp + buf */
+	int			lv_flags;	/* lv flags */
 };
 
 extern struct kmem_cache *xfs_log_vec_cache;
@@ -42,6 +45,7 @@ static inline void
 xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec,
 		int data_len)
 {
+	struct xfs_log_iovec	*lvec = lv->lv_iovecp;
 	struct xlog_op_header	*oph = vec->i_addr;
 	int			len;
 
@@ -71,7 +75,7 @@ xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec,
 	vec->i_len = len;
 
 	/* Catch buffer overruns */
-	ASSERT((void *)lv->lv_buf + lv->lv_bytes <= (void *)lv + lv->lv_size);
+	ASSERT((void *)lv->lv_buf + lv->lv_bytes <= (void *)lvec + lv->lv_size);
 }
 
 /*
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index f51cbc6405c1..7cc9ed0aa14a 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -219,8 +219,7 @@ static inline int
 xlog_cil_iovec_space(
 	uint	niovecs)
 {
-	return round_up((sizeof(struct xfs_log_vec) +
-					niovecs * sizeof(struct xfs_log_iovec)),
+	return round_up(niovecs * sizeof(struct xfs_log_iovec),
 			sizeof(uint64_t));
 }
 
@@ -279,6 +278,7 @@ xlog_cil_alloc_shadow_bufs(
 
 	list_for_each_entry(lip, &tp->t_items, li_trans) {
 		struct xfs_log_vec *lv;
+		struct xfs_log_iovec *lvec;
 		int	niovecs = 0;
 		int	nbytes = 0;
 		int	buf_size;
@@ -330,8 +330,8 @@ xlog_cil_alloc_shadow_bufs(
 		 * if we have no shadow buffer, or it is too small, we need to
 		 * reallocate it.
 		 */
-		if (!lip->li_lv_shadow ||
-		    buf_size > lip->li_lv_shadow->lv_size) {
+		lv = lip->li_lv_shadow;
+		if (!lv || buf_size > lv->lv_size) {
 			/*
 			 * We free and allocate here as a realloc would copy
 			 * unnecessary data. We don't use kvzalloc() for the
@@ -339,18 +339,24 @@ xlog_cil_alloc_shadow_bufs(
 			 * the buffer, only the log vector header and the iovec
 			 * storage.
 			 */
-			kvfree(lip->li_lv_shadow);
-			lv = xlog_kvmalloc(buf_size);
+			if (lv)
+				kvfree(lv->lv_iovecp);
+			else
+				lv = kmem_cache_alloc(xfs_log_vec_cache,
+						GFP_KERNEL | __GFP_NOFAIL);
 
-			memset(lv, 0, xlog_cil_iovec_space(niovecs));
+			memset(lv, 0, sizeof(struct xfs_log_vec));
+			lvec = xlog_kvmalloc(buf_size);
+			memset(lvec, 0, xlog_cil_iovec_space(niovecs));
 
+			lv->lv_flags |= XFS_LOG_VEC_DYNAMIC;
 			INIT_LIST_HEAD(&lv->lv_list);
 			lv->lv_item = lip;
 			lv->lv_size = buf_size;
 			if (ordered)
 				lv->lv_buf_len = XFS_LOG_VEC_ORDERED;
 			else
-				lv->lv_iovecp = (struct xfs_log_iovec *)&lv[1];
+				lv->lv_iovecp = lvec;
 			lip->li_lv_shadow = lv;
 		} else {
 			/* same or smaller, optimise common overwrite case */
@@ -366,9 +372,9 @@ xlog_cil_alloc_shadow_bufs(
 		lv->lv_niovecs = niovecs;
 
 		/* The allocated data region lies beyond the iovec region */
-		lv->lv_buf = (char *)lv + xlog_cil_iovec_space(niovecs);
+		lv->lv_buf = (char *)lv->lv_iovecp +
+				xlog_cil_iovec_space(niovecs);
 	}
-
 }
 
 /*
@@ -502,7 +508,7 @@ xlog_cil_insert_format_items(
 			/* reset the lv buffer information for new formatting */
 			lv->lv_buf_len = 0;
 			lv->lv_bytes = 0;
-			lv->lv_buf = (char *)lv +
+			lv->lv_buf = (char *)lv->lv_iovecp +
 					xlog_cil_iovec_space(lv->lv_niovecs);
 		} else {
 			/* switch to shadow buffer! */
@@ -703,7 +709,7 @@ xlog_cil_free_logvec(
 	while (!list_empty(lv_chain)) {
 		lv = list_first_entry(lv_chain, struct xfs_log_vec, lv_list);
 		list_del_init(&lv->lv_list);
-		kvfree(lv);
+		kmem_cache_free(xfs_log_vec_cache, lv);
 	}
 }
 
@@ -1544,7 +1550,8 @@ xlog_cil_process_intents(
 		set_bit(XFS_LI_WHITEOUT, &ilip->li_flags);
 		trace_xfs_cil_whiteout_mark(ilip);
 		len += ilip->li_lv->lv_bytes;
-		kvfree(ilip->li_lv);
+		kvfree(ilip->li_lv->lv_iovecp);
+		kmem_cache_free(xfs_log_vec_cache, ilip->li_lv);
 		ilip->li_lv = NULL;
 
 		xfs_trans_del_item(lip);
-- 
2.39.3