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 the
already-read byte range (0 to file->offset) so that kernel readahead
pages for upcoming reads are preserved while all read data is evicted.

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-read byte range from the page cache
+         * so that kernel readahead for upcoming reads is preserved. */
+        if (ctx->file_cache_advise && file->offset > 0) {
+            posix_fadvise(file->fd, 0, file->offset,
+                          POSIX_FADV_DONTNEED);
+        }
+#endif
+
 #ifdef FLB_HAVE_SQLDB
         if (file->config->db) {
             flb_tail_db_file_offset(file, file->config);