in_tail: fix file_cache_advise causing high disk IOPS

The posix_fadvise(POSIX_FADV_DONTNEED) call was placed before the
read and evicted the entire file from the page cache on every chunk
cycle. This forced every subsequent read to go to disk, causing
excessive IOPS.

Move the call to after read and processing, and scope it to only
the already-consumed byte range (0 to stream_offset) so that kernel
readahead pages for upcoming reads are preserved.

Signed-off-by: Anuj Singh <singholt@amazon.com>

Author: singholt

plugins/in_tail/tail_file.c

@@ -1698,15 +1698,6 @@ int flb_tail_file_chunk(struct flb_tail_file *file)
         file_buffer_capacity = (file->buf_size - file->buf_len) - 1;
     }
 
-    #ifdef __linux__
-    if (ctx->file_cache_advise) {
-        if (posix_fadvise(file->fd, 0, 0, POSIX_FADV_DONTNEED) == -1) {
-            flb_errno();
-            flb_plg_error(ctx->ins, "error during posix_fadvise");
-        }
-    }
-    #endif
-
     read_size = file_buffer_capacity;
 
     if (file->decompression_context != NULL) {
@@ -1822,6 +1813,15 @@ int flb_tail_file_chunk(struct flb_tail_file *file)
         file->buf_len -= processed_bytes;
         file->buf_data[file->buf_len] = '\0';
 
+#ifdef __linux__
+        /* Evict only the already-processed byte range from the page cache
+         * so that kernel readahead for upcoming reads is preserved. */
+        if (ctx->file_cache_advise && file->stream_offset > 0) {
+            posix_fadvise(file->fd, 0, file->stream_offset,
+                          POSIX_FADV_DONTNEED);
+        }
+#endif
+
 #ifdef FLB_HAVE_SQLDB
         if (file->config->db) {
             flb_tail_db_file_offset(file, file->config);